Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5393 in Layer 25
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.3976. Min Range: -7.3976
Max Act: 7.3976. Min Act: -0.1700
Data Index: 2731895 (Open Web Text)
Max Activating Token Index: 609
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.3976. Min Range: -7.3976
Max Act: 7.3039. Min Act: -0.1700
Data Index: 5968129 (Open Web Text)
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.3976. Min Range: -7.3976
Max Act: 7.3039. Min Act: -0.1700
Data Index: 3174281 (Open Web Text)
Max Activating Token Index: 373
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.3976. Min Range: -7.3976
Max Act: 7.2726. Min Act: -0.1700
Data Index: 1071038 (Open Web Text)
Max Activating Token Index: 258
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.3976. Min Range: -7.3976
Max Act: 7.1476. Min Act: -0.1700
Data Index: 1236452 (Open Web Text)
Max Activating Token Index: 896
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.3976. Min Range: -7.3976
Max Act: 7.0539. Min Act: -0.1700
Data Index: 6543593 (Open Web Text)
Max Activating Token Index: 849
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.3976. Min Range: -7.3976
Max Act: 7.0226. Min Act: -0.1700
Data Index: 1545936 (Open Web Text)
Max Activating Token Index: 736
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.3976. Min Range: -7.3976
Max Act: 7.0226. Min Act: -0.1700
Data Index: 8585927 (Open Web Text)
Max Activating Token Index: 175
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.3976. Min Range: -7.3976
Max Act: 6.9289. Min Act: -0.1700
Data Index: 8725501 (Open Web Text)
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.3976. Min Range: -7.3976
Max Act: 6.9601. Min Act: -0.1700
Data Index: 7005621 (Open Web Text)
Max Activating Token Index: 739
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.3976. Min Range: -7.3976
Max Act: 6.9289. Min Act: -0.1700
Data Index: 2365127 (Open Web Text)
Max Activating Token Index: 896
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.3976. Min Range: -7.3976
Max Act: 6.8976. Min Act: -0.1700
Data Index: 6399246 (Open Web Text)
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.3976. Min Range: -7.3976
Max Act: 6.8976. Min Act: -0.1700
Data Index: 5269042 (Open Web Text)
Max Activating Token Index: 882
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.3976. Min Range: -7.3976
Max Act: 6.8039. Min Act: -0.1700
Data Index: 5509062 (Open Web Text)
Max Activating Token Index: 945
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.3976. Min Range: -7.3976
Max Act: 6.8351. Min Act: -0.1700
Data Index: 4513023 (Open Web Text)
Max Activating Token Index: 759
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.3976. Min Range: -7.3976
Max Act: 6.8039. Min Act: -0.1700
Data Index: 44796 (Open Web Text)
Max Activating Token Index: 974
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.3976. Min Range: -7.3976
Max Act: 6.7726. Min Act: -0.1700
Data Index: 3282503 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.3976. Min Range: -7.3976
Max Act: 6.7414. Min Act: -0.1700
Data Index: 3287242 (Open Web Text)
Max Activating Token Index: 64
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.3976. Min Range: -7.3976
Max Act: 6.7414. Min Act: -0.1700
Data Index: 6133942 (Open Web Text)
Max Activating Token Index: 840
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.3976. Min Range: -7.3976
Max Act: 6.7414. Min Act: -0.1700
Data Index: 6777292 (Open Web Text)
Max Activating Token Index: 423
Click toggle to see full text
Truncated
Full Text #19