Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2563 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.3355. Min Range: -7.3355
Max Act: 7.3355. Min Act: -0.1700
Data Index: 6792080 (Open Web Text)
Max Activating Token Index: 419
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.3355. Min Range: -7.3355
Max Act: 7.1480. Min Act: -0.1700
Data Index: 1270925 (Open Web Text)
Max Activating Token Index: 961
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.3355. Min Range: -7.3355
Max Act: 7.1792. Min Act: -0.1700
Data Index: 1397969 (Open Web Text)
Max Activating Token Index: 194
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.3355. Min Range: -7.3355
Max Act: 7.1480. Min Act: -0.1700
Data Index: 5114541 (Open Web Text)
Max Activating Token Index: 527
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.3355. Min Range: -7.3355
Max Act: 7.1480. Min Act: -0.1700
Data Index: 3782203 (Open Web Text)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.3355. Min Range: -7.3355
Max Act: 7.1480. Min Act: -0.1700
Data Index: 801296 (Open Web Text)
Max Activating Token Index: 839
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.3355. Min Range: -7.3355
Max Act: 7.1167. Min Act: -0.1700
Data Index: 2137203 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.3355. Min Range: -7.3355
Max Act: 7.0855. Min Act: -0.1700
Data Index: 4780312 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.3355. Min Range: -7.3355
Max Act: 7.0542. Min Act: -0.1700
Data Index: 7824490 (Open Web Text)
Max Activating Token Index: 152
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.3355. Min Range: -7.3355
Max Act: 7.0542. Min Act: -0.1700
Data Index: 6792079 (Open Web Text)
Max Activating Token Index: 432
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.3355. Min Range: -7.3355
Max Act: 7.0542. Min Act: -0.1700
Data Index: 6097731 (Open Web Text)
Max Activating Token Index: 893
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.3355. Min Range: -7.3355
Max Act: 7.0542. Min Act: -0.1700
Data Index: 5114547 (Open Web Text)
Max Activating Token Index: 721
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.3355. Min Range: -7.3355
Max Act: 7.0855. Min Act: -0.1700
Data Index: 7093699 (Open Web Text)
Max Activating Token Index: 173
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.3355. Min Range: -7.3355
Max Act: 7.0855. Min Act: -0.1700
Data Index: 8766104 (Open Web Text)
Max Activating Token Index: 813
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.3355. Min Range: -7.3355
Max Act: 7.0230. Min Act: -0.1700
Data Index: 2395832 (Open Web Text)
Max Activating Token Index: 875
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.3355. Min Range: -7.3355
Max Act: 7.0542. Min Act: -0.1700
Data Index: 4446754 (Open Web Text)
Max Activating Token Index: 840
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.3355. Min Range: -7.3355
Max Act: 7.0230. Min Act: -0.1700
Data Index: 6561762 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.3355. Min Range: -7.3355
Max Act: 7.0542. Min Act: -0.1700
Data Index: 3146040 (Open Web Text)
Max Activating Token Index: 991
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.3355. Min Range: -7.3355
Max Act: 6.9917. Min Act: -0.1700
Data Index: 8138119 (Open Web Text)
Max Activating Token Index: 445
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.3355. Min Range: -7.3355
Max Act: 6.9917. Min Act: -0.1700
Data Index: 4076885 (Open Web Text)
Max Activating Token Index: 993
Click toggle to see full text
Truncated
Full Text #19