Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3396 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.3403. Min Range: -5.3403
Max Act: 5.3403. Min Act: -0.1700
Data Index: 4313450 (Open Web Text)
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.3403. Min Range: -5.3403
Max Act: 5.2466. Min Act: -0.1700
Data Index: 6248887 (Open Web Text)
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.3403. Min Range: -5.3403
Max Act: 5.2778. Min Act: -0.1700
Data Index: 6927034 (Open Web Text)
Max Activating Token Index: 911
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.3403. Min Range: -5.3403
Max Act: 5.2466. Min Act: -0.1700
Data Index: 4484602 (Open Web Text)
Max Activating Token Index: 251
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.3403. Min Range: -5.3403
Max Act: 5.2466. Min Act: -0.1700
Data Index: 2329018 (Open Web Text)
Max Activating Token Index: 852
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.3403. Min Range: -5.3403
Max Act: 5.2466. Min Act: -0.1700
Data Index: 7085341 (Open Web Text)
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.3403. Min Range: -5.3403
Max Act: 5.2153. Min Act: -0.1700
Data Index: 7230488 (Open Web Text)
Max Activating Token Index: 543
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.3403. Min Range: -5.3403
Max Act: 5.2153. Min Act: -0.1700
Data Index: 1101758 (Open Web Text)
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.3403. Min Range: -5.3403
Max Act: 5.1841. Min Act: -0.1700
Data Index: 1733080 (Open Web Text)
Max Activating Token Index: 190
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.3403. Min Range: -5.3403
Max Act: 5.1841. Min Act: -0.1700
Data Index: 720062 (Open Web Text)
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.3403. Min Range: -5.3403
Max Act: 5.1841. Min Act: -0.1700
Data Index: 6544508 (Open Web Text)
Max Activating Token Index: 178
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.3403. Min Range: -5.3403
Max Act: 5.1528. Min Act: -0.1700
Data Index: 5608561 (Open Web Text)
Max Activating Token Index: 163
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.3403. Min Range: -5.3403
Max Act: 5.1528. Min Act: -0.1700
Data Index: 3948182 (Open Web Text)
Max Activating Token Index: 1002
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.3403. Min Range: -5.3403
Max Act: 5.1216. Min Act: -0.1700
Data Index: 599377 (Open Web Text)
Max Activating Token Index: 572
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.3403. Min Range: -5.3403
Max Act: 5.1216. Min Act: -0.1700
Data Index: 4660742 (Open Web Text)
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.3403. Min Range: -5.3403
Max Act: 5.0903. Min Act: -0.1700
Data Index: 3816838 (Open Web Text)
Max Activating Token Index: 717
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.3403. Min Range: -5.3403
Max Act: 5.1216. Min Act: -0.1700
Data Index: 6825767 (Open Web Text)
Max Activating Token Index: 417
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.3403. Min Range: -5.3403
Max Act: 5.0903. Min Act: -0.1700
Data Index: 495382 (Open Web Text)
Max Activating Token Index: 461
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.3403. Min Range: -5.3403
Max Act: 5.0903. Min Act: -0.1700
Data Index: 598415 (Open Web Text)
Max Activating Token Index: 836
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.3403. Min Range: -5.3403
Max Act: 5.0903. Min Act: -0.1700
Data Index: 1597959 (Open Web Text)
Max Activating Token Index: 491
Click toggle to see full text
Truncated
Full Text #19