Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3250 in Layer 13
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.4307. Min Range: -5.4307
Max Act: 5.4307. Min Act: -0.1700
Data Index: 1141676 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.4307. Min Range: -5.4307
Max Act: 5.3057. Min Act: -0.1700
Data Index: 4403670 (Open Web Text)
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.4307. Min Range: -5.4307
Max Act: 5.2120. Min Act: -0.1700
Data Index: 4403668 (Open Web Text)
Max Activating Token Index: 75
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.4307. Min Range: -5.4307
Max Act: 5.1182. Min Act: -0.1700
Data Index: 7194 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.4307. Min Range: -5.4307
Max Act: 5.0870. Min Act: -0.1700
Data Index: 4536661 (Open Web Text)
Max Activating Token Index: 469
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.4307. Min Range: -5.4307
Max Act: 5.0557. Min Act: -0.1700
Data Index: 3565893 (Open Web Text)
Max Activating Token Index: 391
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.4307. Min Range: -5.4307
Max Act: 5.0557. Min Act: -0.1700
Data Index: 4303343 (Open Web Text)
Max Activating Token Index: 249
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.4307. Min Range: -5.4307
Max Act: 5.0557. Min Act: -0.1700
Data Index: 1498538 (Open Web Text)
Max Activating Token Index: 729
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.4307. Min Range: -5.4307
Max Act: 4.9932. Min Act: -0.1700
Data Index: 8393047 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.4307. Min Range: -5.4307
Max Act: 4.9932. Min Act: -0.1700
Data Index: 1141677 (Open Web Text)
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.4307. Min Range: -5.4307
Max Act: 4.9307. Min Act: -0.1700
Data Index: 2246185 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.4307. Min Range: -5.4307
Max Act: 4.9307. Min Act: -0.1700
Data Index: 5846846 (Open Web Text)
Max Activating Token Index: 95
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.4307. Min Range: -5.4307
Max Act: 4.9307. Min Act: -0.1700
Data Index: 4340307 (Open Web Text)
Max Activating Token Index: 945
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.4307. Min Range: -5.4307
Max Act: 4.9307. Min Act: -0.1700
Data Index: 8393048 (Open Web Text)
Max Activating Token Index: 400
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.4307. Min Range: -5.4307
Max Act: 4.8995. Min Act: -0.1700
Data Index: 4307806 (Open Web Text)
Max Activating Token Index: 54
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.4307. Min Range: -5.4307
Max Act: 4.9307. Min Act: -0.1700
Data Index: 3641933 (Open Web Text)
Max Activating Token Index: 31
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.4307. Min Range: -5.4307
Max Act: 4.8682. Min Act: -0.1700
Data Index: 6889400 (Open Web Text)
Max Activating Token Index: 23
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.4307. Min Range: -5.4307
Max Act: 4.8682. Min Act: -0.1700
Data Index: 3036484 (Open Web Text)
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.4307. Min Range: -5.4307
Max Act: 4.8682. Min Act: -0.1700
Data Index: 1397242 (Open Web Text)
Max Activating Token Index: 412
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.4307. Min Range: -5.4307
Max Act: 4.8682. Min Act: -0.1700
Data Index: 8067233 (Open Web Text)
Max Activating Token Index: 1002
Click toggle to see full text
Truncated
Full Text #19