Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3980 in Layer 34
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 8.7682. Min Range: -8.7682
Max Act: 8.7682. Min Act: -0.1700
Data Index: 2895467 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.7682. Min Range: -8.7682
Max Act: 8.0807. Min Act: -0.1700
Data Index: 6592371 (Open Web Text)
Max Activating Token Index: 715
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.7682. Min Range: -8.7682
Max Act: 7.8619. Min Act: -0.1700
Data Index: 5679565 (Open Web Text)
Max Activating Token Index: 941
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.7682. Min Range: -8.7682
Max Act: 7.8932. Min Act: -0.1700
Data Index: 2313350 (Open Web Text)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.7682. Min Range: -8.7682
Max Act: 7.8307. Min Act: -0.1700
Data Index: 6607059 (Open Web Text)
Max Activating Token Index: 500
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.7682. Min Range: -8.7682
Max Act: 7.8307. Min Act: -0.1700
Data Index: 2770535 (Open Web Text)
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.7682. Min Range: -8.7682
Max Act: 7.7369. Min Act: -0.1700
Data Index: 200306 (Open Web Text)
Max Activating Token Index: 664
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.7682. Min Range: -8.7682
Max Act: 7.7057. Min Act: -0.1700
Data Index: 5374372 (Open Web Text)
Max Activating Token Index: 183
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.7682. Min Range: -8.7682
Max Act: 7.6744. Min Act: -0.1700
Data Index: 2707270 (Open Web Text)
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.7682. Min Range: -8.7682
Max Act: 7.7057. Min Act: -0.1700
Data Index: 318070 (Open Web Text)
Max Activating Token Index: 871
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.7682. Min Range: -8.7682
Max Act: 7.7369. Min Act: -0.1700
Data Index: 8061657 (Open Web Text)
Max Activating Token Index: 756
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.7682. Min Range: -8.7682
Max Act: 7.6744. Min Act: -0.1700
Data Index: 5521138 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.7682. Min Range: -8.7682
Max Act: 7.6744. Min Act: -0.1700
Data Index: 6023700 (Open Web Text)
Max Activating Token Index: 932
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.7682. Min Range: -8.7682
Max Act: 7.5807. Min Act: -0.1700
Data Index: 3146234 (Open Web Text)
Max Activating Token Index: 362
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.7682. Min Range: -8.7682
Max Act: 7.6432. Min Act: -0.1700
Data Index: 3244545 (Open Web Text)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.7682. Min Range: -8.7682
Max Act: 7.5807. Min Act: -0.1700
Data Index: 7449168 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.7682. Min Range: -8.7682
Max Act: 7.5494. Min Act: -0.1700
Data Index: 5283769 (Open Web Text)
Max Activating Token Index: 936
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.7682. Min Range: -8.7682
Max Act: 7.5807. Min Act: -0.1700
Data Index: 6002782 (Open Web Text)
Max Activating Token Index: 129
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.7682. Min Range: -8.7682
Max Act: 7.6119. Min Act: -0.1700
Data Index: 5811273 (Open Web Text)
Max Activating Token Index: 368
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.7682. Min Range: -8.7682
Max Act: 7.5494. Min Act: -0.1700
Data Index: 3169901 (Open Web Text)
Max Activating Token Index: 928
Click toggle to see full text
Truncated
Full Text #19