Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3713 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 10.7562. Min Range: -10.7562
Max Act: 10.7562. Min Act: -0.1700
Data Index: 1182073 (Open Web Text)
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 10.7562. Min Range: -10.7562
Max Act: 10.6312. Min Act: -0.1700
Data Index: 1701367 (Open Web Text)
Max Activating Token Index: 487
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 10.7562. Min Range: -10.7562
Max Act: 10.5687. Min Act: -0.1700
Data Index: 6282533 (Open Web Text)
Max Activating Token Index: 699
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 10.7562. Min Range: -10.7562
Max Act: 10.5687. Min Act: -0.1700
Data Index: 7962223 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 10.7562. Min Range: -10.7562
Max Act: 10.5062. Min Act: -0.1700
Data Index: 3195718 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 10.7562. Min Range: -10.7562
Max Act: 10.5062. Min Act: -0.1700
Data Index: 8342548 (Open Web Text)
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 10.7562. Min Range: -10.7562
Max Act: 10.3812. Min Act: -0.1700
Data Index: 5491164 (Open Web Text)
Max Activating Token Index: 496
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 10.7562. Min Range: -10.7562
Max Act: 10.3187. Min Act: -0.1700
Data Index: 3081552 (Open Web Text)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 10.7562. Min Range: -10.7562
Max Act: 10.3812. Min Act: -0.1700
Data Index: 5518929 (Open Web Text)
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 10.7562. Min Range: -10.7562
Max Act: 10.2562. Min Act: -0.1700
Data Index: 5028519 (Open Web Text)
Max Activating Token Index: 474
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 10.7562. Min Range: -10.7562
Max Act: 10.3812. Min Act: -0.1700
Data Index: 4007605 (Open Web Text)
Max Activating Token Index: 823
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 10.7562. Min Range: -10.7562
Max Act: 10.2562. Min Act: -0.1700
Data Index: 1213170 (Open Web Text)
Max Activating Token Index: 547
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 10.7562. Min Range: -10.7562
Max Act: 10.2562. Min Act: -0.1700
Data Index: 2275385 (Open Web Text)
Max Activating Token Index: 886
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 10.7562. Min Range: -10.7562
Max Act: 10.3187. Min Act: -0.1700
Data Index: 4343239 (Open Web Text)
Max Activating Token Index: 616
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 10.7562. Min Range: -10.7562
Max Act: 10.2562. Min Act: -0.1700
Data Index: 2066330 (Open Web Text)
Max Activating Token Index: 199
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 10.7562. Min Range: -10.7562
Max Act: 10.2562. Min Act: -0.1700
Data Index: 8093300 (Open Web Text)
Max Activating Token Index: 983
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 10.7562. Min Range: -10.7562
Max Act: 10.2562. Min Act: -0.1700
Data Index: 3277611 (Open Web Text)
Max Activating Token Index: 176
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 10.7562. Min Range: -10.7562
Max Act: 10.2562. Min Act: -0.1700
Data Index: 1886312 (Open Web Text)
Max Activating Token Index: 418
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 10.7562. Min Range: -10.7562
Max Act: 10.2562. Min Act: -0.1700
Data Index: 6411598 (Open Web Text)
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 10.7562. Min Range: -10.7562
Max Act: 10.1937. Min Act: -0.1700
Data Index: 688280 (Open Web Text)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #19