Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4745 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.8377. Min Range: -5.8377
Max Act: 5.8377. Min Act: -0.1700
Data Index: 748295 (Open Web Text)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.8377. Min Range: -5.8377
Max Act: 5.8377. Min Act: -0.1700
Data Index: 8656464 (Open Web Text)
Max Activating Token Index: 274
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.8377. Min Range: -5.8377
Max Act: 5.8377. Min Act: -0.1700
Data Index: 4519487 (Open Web Text)
Max Activating Token Index: 801
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.8377. Min Range: -5.8377
Max Act: 5.8377. Min Act: -0.1700
Data Index: 3401987 (Open Web Text)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.8377. Min Range: -5.8377
Max Act: 5.7127. Min Act: -0.1700
Data Index: 1662837 (Open Web Text)
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.8377. Min Range: -5.8377
Max Act: 5.7127. Min Act: -0.1700
Data Index: 3501445 (Open Web Text)
Max Activating Token Index: 81
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.8377. Min Range: -5.8377
Max Act: 5.6814. Min Act: -0.1700
Data Index: 5302288 (Open Web Text)
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.8377. Min Range: -5.8377
Max Act: 5.6814. Min Act: -0.1700
Data Index: 6335659 (Open Web Text)
Max Activating Token Index: 608
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.8377. Min Range: -5.8377
Max Act: 5.6502. Min Act: -0.1700
Data Index: 4169661 (Open Web Text)
Max Activating Token Index: 340
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.8377. Min Range: -5.8377
Max Act: 5.6502. Min Act: -0.1700
Data Index: 8225732 (Open Web Text)
Max Activating Token Index: 983
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.8377. Min Range: -5.8377
Max Act: 5.5877. Min Act: -0.1700
Data Index: 6800068 (Open Web Text)
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.8377. Min Range: -5.8377
Max Act: 5.5877. Min Act: -0.1700
Data Index: 5870641 (Open Web Text)
Max Activating Token Index: 427
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.8377. Min Range: -5.8377
Max Act: 5.5564. Min Act: -0.1700
Data Index: 5870639 (Open Web Text)
Max Activating Token Index: 751
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.8377. Min Range: -5.8377
Max Act: 5.5564. Min Act: -0.1700
Data Index: 1662839 (Open Web Text)
Max Activating Token Index: 197
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.8377. Min Range: -5.8377
Max Act: 5.5252. Min Act: -0.1700
Data Index: 4199492 (Open Web Text)
Max Activating Token Index: 682
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.8377. Min Range: -5.8377
Max Act: 5.5564. Min Act: -0.1700
Data Index: 4598778 (Open Web Text)
Max Activating Token Index: 738
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.8377. Min Range: -5.8377
Max Act: 5.4939. Min Act: -0.1700
Data Index: 857291 (Open Web Text)
Max Activating Token Index: 383
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.8377. Min Range: -5.8377
Max Act: 5.4939. Min Act: -0.1700
Data Index: 3985857 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.8377. Min Range: -5.8377
Max Act: 5.4939. Min Act: -0.1700
Data Index: 4412940 (Open Web Text)
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.8377. Min Range: -5.8377
Max Act: 5.4939. Min Act: -0.1700
Data Index: 171733 (Open Web Text)
Max Activating Token Index: 566
Click toggle to see full text
Truncated
Full Text #19