Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3964 in Layer 26
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.9809. Min Range: -4.9809
Max Act: 4.9809. Min Act: -0.1700
Data Index: 4680513 (Open Web Text)
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.9809. Min Range: -4.9809
Max Act: 4.9497. Min Act: -0.1700
Data Index: 7083443 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.9809. Min Range: -4.9809
Max Act: 4.8872. Min Act: -0.1700
Data Index: 7999018 (Open Web Text)
Max Activating Token Index: 179
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.9809. Min Range: -4.9809
Max Act: 4.8559. Min Act: -0.1700
Data Index: 8372532 (Open Web Text)
Max Activating Token Index: 358
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.9809. Min Range: -4.9809
Max Act: 4.8247. Min Act: -0.1700
Data Index: 7037717 (Open Web Text)
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.9809. Min Range: -4.9809
Max Act: 4.7934. Min Act: -0.1700
Data Index: 2191110 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.9809. Min Range: -4.9809
Max Act: 4.7934. Min Act: -0.1700
Data Index: 1200234 (Open Web Text)
Max Activating Token Index: 759
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.9809. Min Range: -4.9809
Max Act: 4.7622. Min Act: -0.1700
Data Index: 493326 (Open Web Text)
Max Activating Token Index: 132
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.9809. Min Range: -4.9809
Max Act: 4.7309. Min Act: -0.1700
Data Index: 7420030 (Open Web Text)
Max Activating Token Index: 253
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.9809. Min Range: -4.9809
Max Act: 4.7622. Min Act: -0.1700
Data Index: 6675383 (Open Web Text)
Max Activating Token Index: 807
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.9809. Min Range: -4.9809
Max Act: 4.7622. Min Act: -0.1700
Data Index: 4643412 (Open Web Text)
Max Activating Token Index: 272
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.9809. Min Range: -4.9809
Max Act: 4.7309. Min Act: -0.1700
Data Index: 1937178 (Open Web Text)
Max Activating Token Index: 707
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.9809. Min Range: -4.9809
Max Act: 4.6997. Min Act: -0.1700
Data Index: 7811244 (Open Web Text)
Max Activating Token Index: 469
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.9809. Min Range: -4.9809
Max Act: 4.7309. Min Act: -0.1700
Data Index: 2429062 (Open Web Text)
Max Activating Token Index: 779
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.9809. Min Range: -4.9809
Max Act: 4.7309. Min Act: -0.1700
Data Index: 4671408 (Open Web Text)
Max Activating Token Index: 33
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.9809. Min Range: -4.9809
Max Act: 4.6684. Min Act: -0.1700
Data Index: 6295582 (Open Web Text)
Max Activating Token Index: 804
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.9809. Min Range: -4.9809
Max Act: 4.6997. Min Act: -0.1700
Data Index: 6581169 (Open Web Text)
Max Activating Token Index: 434
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.9809. Min Range: -4.9809
Max Act: 4.7309. Min Act: -0.1700
Data Index: 7415048 (Open Web Text)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.9809. Min Range: -4.9809
Max Act: 4.6997. Min Act: -0.1700
Data Index: 4162478 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.9809. Min Range: -4.9809
Max Act: 4.6997. Min Act: -0.1700
Data Index: 310235 (Open Web Text)
Max Activating Token Index: 318
Click toggle to see full text
Truncated
Full Text #19