Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5212 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.7130. Min Range: -6.7130
Max Act: 6.7130. Min Act: -0.1700
Data Index: 7246321 (Open Web Text)
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.7130. Min Range: -6.7130
Max Act: 6.6818. Min Act: -0.1700
Data Index: 5687312 (Open Web Text)
Max Activating Token Index: 682
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.7130. Min Range: -6.7130
Max Act: 6.4318. Min Act: -0.1700
Data Index: 1513658 (Open Web Text)
Max Activating Token Index: 690
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.7130. Min Range: -6.7130
Max Act: 6.4318. Min Act: -0.1700
Data Index: 2309750 (Open Web Text)
Max Activating Token Index: 720
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.7130. Min Range: -6.7130
Max Act: 6.3693. Min Act: -0.1700
Data Index: 4367683 (Open Web Text)
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.7130. Min Range: -6.7130
Max Act: 6.2443. Min Act: -0.1700
Data Index: 7834587 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.7130. Min Range: -6.7130
Max Act: 6.0880. Min Act: -0.1700
Data Index: 5811243 (Open Web Text)
Max Activating Token Index: 546
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.7130. Min Range: -6.7130
Max Act: 6.1193. Min Act: -0.1700
Data Index: 7832974 (Open Web Text)
Max Activating Token Index: 193
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.7130. Min Range: -6.7130
Max Act: 6.0568. Min Act: -0.1700
Data Index: 8437518 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.7130. Min Range: -6.7130
Max Act: 6.0568. Min Act: -0.1700
Data Index: 4319293 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.7130. Min Range: -6.7130
Max Act: 6.0568. Min Act: -0.1700
Data Index: 4713408 (Open Web Text)
Max Activating Token Index: 466
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.7130. Min Range: -6.7130
Max Act: 6.0568. Min Act: -0.1700
Data Index: 4332115 (Open Web Text)
Max Activating Token Index: 515
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.7130. Min Range: -6.7130
Max Act: 5.9943. Min Act: -0.1700
Data Index: 2404330 (Open Web Text)
Max Activating Token Index: 907
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.7130. Min Range: -6.7130
Max Act: 5.9630. Min Act: -0.1700
Data Index: 4855835 (Open Web Text)
Max Activating Token Index: 811
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.7130. Min Range: -6.7130
Max Act: 5.9630. Min Act: -0.1700
Data Index: 3330474 (Open Web Text)
Max Activating Token Index: 825
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.7130. Min Range: -6.7130
Max Act: 5.9318. Min Act: -0.1700
Data Index: 5750908 (Open Web Text)
Max Activating Token Index: 462
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.7130. Min Range: -6.7130
Max Act: 5.9630. Min Act: -0.1700
Data Index: 8661152 (Open Web Text)
Max Activating Token Index: 119
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.7130. Min Range: -6.7130
Max Act: 5.9318. Min Act: -0.1700
Data Index: 8680782 (Open Web Text)
Max Activating Token Index: 604
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.7130. Min Range: -6.7130
Max Act: 5.9318. Min Act: -0.1700
Data Index: 925527 (Open Web Text)
Max Activating Token Index: 337
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.7130. Min Range: -6.7130
Max Act: 5.9005. Min Act: -0.1700
Data Index: 5699634 (Open Web Text)
Max Activating Token Index: 306
Click toggle to see full text
Truncated
Full Text #19