Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3174 in Layer 37
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.6459. Min Range: -6.6459
Max Act: 6.6459. Min Act: -0.1700
Data Index: 2387228 (Open Web Text)
Max Activating Token Index: 357
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.6459. Min Range: -6.6459
Max Act: 6.2709. Min Act: -0.1700
Data Index: 765268 (Open Web Text)
Max Activating Token Index: 1009
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.6459. Min Range: -6.6459
Max Act: 6.2397. Min Act: -0.1700
Data Index: 3666030 (Open Web Text)
Max Activating Token Index: 108
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.6459. Min Range: -6.6459
Max Act: 6.2397. Min Act: -0.1700
Data Index: 7740513 (Open Web Text)
Max Activating Token Index: 917
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.6459. Min Range: -6.6459
Max Act: 6.2397. Min Act: -0.1700
Data Index: 5199260 (Open Web Text)
Max Activating Token Index: 964
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.6459. Min Range: -6.6459
Max Act: 6.2084. Min Act: -0.1700
Data Index: 4846174 (Open Web Text)
Max Activating Token Index: 847
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.6459. Min Range: -6.6459
Max Act: 6.1772. Min Act: -0.1700
Data Index: 1974972 (Open Web Text)
Max Activating Token Index: 593
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.6459. Min Range: -6.6459
Max Act: 6.0522. Min Act: -0.1700
Data Index: 6253082 (Open Web Text)
Max Activating Token Index: 302
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.6459. Min Range: -6.6459
Max Act: 6.0522. Min Act: -0.1700
Data Index: 6068903 (Open Web Text)
Max Activating Token Index: 449
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.6459. Min Range: -6.6459
Max Act: 5.9897. Min Act: -0.1700
Data Index: 3407784 (Open Web Text)
Max Activating Token Index: 568
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.6459. Min Range: -6.6459
Max Act: 6.0522. Min Act: -0.1700
Data Index: 719290 (Open Web Text)
Max Activating Token Index: 1021
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.6459. Min Range: -6.6459
Max Act: 5.9584. Min Act: -0.1700
Data Index: 4490301 (Open Web Text)
Max Activating Token Index: 173
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.6459. Min Range: -6.6459
Max Act: 5.9584. Min Act: -0.1700
Data Index: 3342819 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.6459. Min Range: -6.6459
Max Act: 5.9584. Min Act: -0.1700
Data Index: 1966284 (Open Web Text)
Max Activating Token Index: 235
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.6459. Min Range: -6.6459
Max Act: 5.9272. Min Act: -0.1700
Data Index: 5075357 (Open Web Text)
Max Activating Token Index: 233
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.6459. Min Range: -6.6459
Max Act: 5.9272. Min Act: -0.1700
Data Index: 5475216 (Open Web Text)
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.6459. Min Range: -6.6459
Max Act: 5.9272. Min Act: -0.1700
Data Index: 7873581 (Open Web Text)
Max Activating Token Index: 254
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.6459. Min Range: -6.6459
Max Act: 5.9272. Min Act: -0.1700
Data Index: 3350807 (Open Web Text)
Max Activating Token Index: 518
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.6459. Min Range: -6.6459
Max Act: 5.9272. Min Act: -0.1700
Data Index: 6528674 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.6459. Min Range: -6.6459
Max Act: 5.8959. Min Act: -0.1700
Data Index: 3742290 (Open Web Text)
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #19