Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1430 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.3562. Min Range: -6.3562
Max Act: 6.3562. Min Act: -0.1700
Data Index: 5553501 (Open Web Text)
Max Activating Token Index: 180
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.3562. Min Range: -6.3562
Max Act: 6.3562. Min Act: -0.1700
Data Index: 7149694 (Open Web Text)
Max Activating Token Index: 884
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.3562. Min Range: -6.3562
Max Act: 6.3250. Min Act: -0.1700
Data Index: 5882151 (Open Web Text)
Max Activating Token Index: 706
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.3562. Min Range: -6.3562
Max Act: 6.3250. Min Act: -0.1700
Data Index: 4129853 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.3562. Min Range: -6.3562
Max Act: 6.2937. Min Act: -0.1700
Data Index: 6996728 (Open Web Text)
Max Activating Token Index: 397
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.3562. Min Range: -6.3562
Max Act: 6.2625. Min Act: -0.1700
Data Index: 521811 (Open Web Text)
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.3562. Min Range: -6.3562
Max Act: 6.2625. Min Act: -0.1700
Data Index: 4528434 (Open Web Text)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.3562. Min Range: -6.3562
Max Act: 6.2625. Min Act: -0.1700
Data Index: 3173932 (Open Web Text)
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.3562. Min Range: -6.3562
Max Act: 6.2625. Min Act: -0.1700
Data Index: 1370333 (Open Web Text)
Max Activating Token Index: 998
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.3562. Min Range: -6.3562
Max Act: 6.2312. Min Act: -0.1700
Data Index: 5654061 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.3562. Min Range: -6.3562
Max Act: 6.2000. Min Act: -0.1700
Data Index: 8212929 (Open Web Text)
Max Activating Token Index: 911
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.3562. Min Range: -6.3562
Max Act: 6.2000. Min Act: -0.1700
Data Index: 2480274 (Open Web Text)
Max Activating Token Index: 387
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.3562. Min Range: -6.3562
Max Act: 6.1375. Min Act: -0.1700
Data Index: 4251824 (Open Web Text)
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.3562. Min Range: -6.3562
Max Act: 6.1687. Min Act: -0.1700
Data Index: 4776811 (Open Web Text)
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.3562. Min Range: -6.3562
Max Act: 6.1375. Min Act: -0.1700
Data Index: 5963775 (Open Web Text)
Max Activating Token Index: 708
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.3562. Min Range: -6.3562
Max Act: 6.1062. Min Act: -0.1700
Data Index: 7501294 (Open Web Text)
Max Activating Token Index: 705
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.3562. Min Range: -6.3562
Max Act: 6.1062. Min Act: -0.1700
Data Index: 4656964 (Open Web Text)
Max Activating Token Index: 975
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.3562. Min Range: -6.3562
Max Act: 6.1375. Min Act: -0.1700
Data Index: 7761302 (Open Web Text)
Max Activating Token Index: 371
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.3562. Min Range: -6.3562
Max Act: 6.1062. Min Act: -0.1700
Data Index: 8584484 (Open Web Text)
Max Activating Token Index: 807
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.3562. Min Range: -6.3562
Max Act: 6.0750. Min Act: -0.1700
Data Index: 5938421 (Open Web Text)
Max Activating Token Index: 1009
Click toggle to see full text
Truncated
Full Text #19