Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2117 in Layer 13
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.7147. Min Range: -5.7147
Max Act: 5.7147. Min Act: -0.1700
Data Index: 8151726 (Open Web Text)
Max Activating Token Index: 1009
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.7147. Min Range: -5.7147
Max Act: 5.7147. Min Act: -0.1700
Data Index: 4870424 (Open Web Text)
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.7147. Min Range: -5.7147
Max Act: 5.6522. Min Act: -0.1700
Data Index: 3895273 (Open Web Text)
Max Activating Token Index: 260
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.7147. Min Range: -5.7147
Max Act: 5.5897. Min Act: -0.1700
Data Index: 785419 (Open Web Text)
Max Activating Token Index: 411
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.7147. Min Range: -5.7147
Max Act: 5.5897. Min Act: -0.1700
Data Index: 6369728 (Open Web Text)
Max Activating Token Index: 427
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.7147. Min Range: -5.7147
Max Act: 5.5584. Min Act: -0.1700
Data Index: 8452322 (Open Web Text)
Max Activating Token Index: 1019
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.7147. Min Range: -5.7147
Max Act: 5.5897. Min Act: -0.1700
Data Index: 6534570 (Open Web Text)
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.7147. Min Range: -5.7147
Max Act: 5.4334. Min Act: -0.1700
Data Index: 7979520 (Open Web Text)
Max Activating Token Index: 451
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.7147. Min Range: -5.7147
Max Act: 5.4334. Min Act: -0.1700
Data Index: 7511388 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.7147. Min Range: -5.7147
Max Act: 5.4647. Min Act: -0.1700
Data Index: 2928405 (Open Web Text)
Max Activating Token Index: 187
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.7147. Min Range: -5.7147
Max Act: 5.4647. Min Act: -0.1700
Data Index: 391803 (Open Web Text)
Max Activating Token Index: 876
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.7147. Min Range: -5.7147
Max Act: 5.4334. Min Act: -0.1700
Data Index: 6550671 (Open Web Text)
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.7147. Min Range: -5.7147
Max Act: 5.4334. Min Act: -0.1700
Data Index: 5104293 (Open Web Text)
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.7147. Min Range: -5.7147
Max Act: 5.4022. Min Act: -0.1700
Data Index: 8287538 (Open Web Text)
Max Activating Token Index: 274
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.7147. Min Range: -5.7147
Max Act: 5.3397. Min Act: -0.1700
Data Index: 393470 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.7147. Min Range: -5.7147
Max Act: 5.3084. Min Act: -0.1700
Data Index: 6646317 (Open Web Text)
Max Activating Token Index: 23
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.7147. Min Range: -5.7147
Max Act: 5.4022. Min Act: -0.1700
Data Index: 4385856 (Open Web Text)
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.7147. Min Range: -5.7147
Max Act: 5.3397. Min Act: -0.1700
Data Index: 7465841 (Open Web Text)
Max Activating Token Index: 317
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.7147. Min Range: -5.7147
Max Act: 5.3084. Min Act: -0.1700
Data Index: 1150690 (Open Web Text)
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.7147. Min Range: -5.7147
Max Act: 5.3084. Min Act: -0.1700
Data Index: 87162 (Open Web Text)
Max Activating Token Index: 541
Click toggle to see full text
Truncated
Full Text #19