Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2939 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.5209. Min Range: -7.5209
Max Act: 7.5209. Min Act: -0.1700
Data Index: 3421074 (Open Web Text)
Max Activating Token Index: 844
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.5209. Min Range: -7.5209
Max Act: 7.3646. Min Act: -0.1700
Data Index: 4190601 (Open Web Text)
Max Activating Token Index: 587
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.5209. Min Range: -7.5209
Max Act: 7.3021. Min Act: -0.1700
Data Index: 8176950 (Open Web Text)
Max Activating Token Index: 838
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.5209. Min Range: -7.5209
Max Act: 7.1771. Min Act: -0.1700
Data Index: 3781834 (Open Web Text)
Max Activating Token Index: 795
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.5209. Min Range: -7.5209
Max Act: 7.1459. Min Act: -0.1700
Data Index: 2987464 (Open Web Text)
Max Activating Token Index: 383
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.5209. Min Range: -7.5209
Max Act: 7.1146. Min Act: -0.1700
Data Index: 6348010 (Open Web Text)
Max Activating Token Index: 669
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.5209. Min Range: -7.5209
Max Act: 7.0521. Min Act: -0.1700
Data Index: 7944667 (Open Web Text)
Max Activating Token Index: 951
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.5209. Min Range: -7.5209
Max Act: 7.0209. Min Act: -0.1700
Data Index: 3604448 (Open Web Text)
Max Activating Token Index: 603
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.5209. Min Range: -7.5209
Max Act: 6.9584. Min Act: -0.1700
Data Index: 1688113 (Open Web Text)
Max Activating Token Index: 296
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.5209. Min Range: -7.5209
Max Act: 6.9271. Min Act: -0.1700
Data Index: 5975979 (Open Web Text)
Max Activating Token Index: 91
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.5209. Min Range: -7.5209
Max Act: 6.9271. Min Act: -0.1700
Data Index: 8782467 (Open Web Text)
Max Activating Token Index: 789
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.5209. Min Range: -7.5209
Max Act: 6.8959. Min Act: -0.1700
Data Index: 6892244 (Open Web Text)
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.5209. Min Range: -7.5209
Max Act: 6.8646. Min Act: -0.1700
Data Index: 1289637 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.5209. Min Range: -7.5209
Max Act: 6.8646. Min Act: -0.1700
Data Index: 6925108 (Open Web Text)
Max Activating Token Index: 472
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.5209. Min Range: -7.5209
Max Act: 6.8021. Min Act: -0.1700
Data Index: 7073574 (Open Web Text)
Max Activating Token Index: 635
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.5209. Min Range: -7.5209
Max Act: 6.8334. Min Act: -0.1700
Data Index: 1995488 (Open Web Text)
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.5209. Min Range: -7.5209
Max Act: 6.8334. Min Act: -0.1700
Data Index: 3735713 (Open Web Text)
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.5209. Min Range: -7.5209
Max Act: 6.8021. Min Act: -0.1700
Data Index: 4933383 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.5209. Min Range: -7.5209
Max Act: 6.8021. Min Act: -0.1700
Data Index: 7565616 (Open Web Text)
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.5209. Min Range: -7.5209
Max Act: 6.7709. Min Act: -0.1700
Data Index: 7533556 (Open Web Text)
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #19