Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3301 in Layer 36
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.7228. Min Range: -6.7228
Max Act: 6.7228. Min Act: -0.1700
Data Index: 5167941 (Open Web Text)
Max Activating Token Index: 387
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.7228. Min Range: -6.7228
Max Act: 6.6603. Min Act: -0.1700
Data Index: 4109756 (Open Web Text)
Max Activating Token Index: 789
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.7228. Min Range: -6.7228
Max Act: 6.6603. Min Act: -0.1700
Data Index: 4614429 (Open Web Text)
Max Activating Token Index: 320
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.7228. Min Range: -6.7228
Max Act: 6.5353. Min Act: -0.1700
Data Index: 3821648 (Open Web Text)
Max Activating Token Index: 638
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.7228. Min Range: -6.7228
Max Act: 6.5041. Min Act: -0.1700
Data Index: 5737717 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.7228. Min Range: -6.7228
Max Act: 6.4416. Min Act: -0.1700
Data Index: 3790940 (Open Web Text)
Max Activating Token Index: 483
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.7228. Min Range: -6.7228
Max Act: 6.4416. Min Act: -0.1700
Data Index: 1894846 (Open Web Text)
Max Activating Token Index: 143
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.7228. Min Range: -6.7228
Max Act: 6.4416. Min Act: -0.1700
Data Index: 7267976 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.7228. Min Range: -6.7228
Max Act: 6.3791. Min Act: -0.1700
Data Index: 4614428 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.7228. Min Range: -6.7228
Max Act: 6.3478. Min Act: -0.1700
Data Index: 4361852 (Open Web Text)
Max Activating Token Index: 851
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.7228. Min Range: -6.7228
Max Act: 6.3478. Min Act: -0.1700
Data Index: 7313740 (Open Web Text)
Max Activating Token Index: 401
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.7228. Min Range: -6.7228
Max Act: 6.2853. Min Act: -0.1700
Data Index: 7068317 (Open Web Text)
Max Activating Token Index: 396
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.7228. Min Range: -6.7228
Max Act: 6.2541. Min Act: -0.1700
Data Index: 3566200 (Open Web Text)
Max Activating Token Index: 178
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.7228. Min Range: -6.7228
Max Act: 6.1916. Min Act: -0.1700
Data Index: 5457722 (Open Web Text)
Max Activating Token Index: 747
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.7228. Min Range: -6.7228
Max Act: 6.1916. Min Act: -0.1700
Data Index: 2443631 (Open Web Text)
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.7228. Min Range: -6.7228
Max Act: 6.1916. Min Act: -0.1700
Data Index: 803867 (Open Web Text)
Max Activating Token Index: 173
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.7228. Min Range: -6.7228
Max Act: 6.1291. Min Act: -0.1700
Data Index: 5013239 (Open Web Text)
Max Activating Token Index: 512
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.7228. Min Range: -6.7228
Max Act: 6.1291. Min Act: -0.1700
Data Index: 6006710 (Open Web Text)
Max Activating Token Index: 35
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.7228. Min Range: -6.7228
Max Act: 6.0978. Min Act: -0.1700
Data Index: 2698734 (Open Web Text)
Max Activating Token Index: 792
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.7228. Min Range: -6.7228
Max Act: 6.0666. Min Act: -0.1700
Data Index: 371512 (Open Web Text)
Max Activating Token Index: 1000
Click toggle to see full text
Truncated
Full Text #19