Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3891 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 5.9355. Min Range: -5.9355
Max Act: 5.9355. Min Act: -0.1700
Data Index: 5039148 (Open Web Text)
Max Activating Token Index: 738
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9355. Min Range: -5.9355
Max Act: 5.9043. Min Act: -0.1700
Data Index: 1965065 (Open Web Text)
Max Activating Token Index: 213
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9355. Min Range: -5.9355
Max Act: 5.8730. Min Act: -0.1700
Data Index: 3816542 (Open Web Text)
Max Activating Token Index: 277
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9355. Min Range: -5.9355
Max Act: 5.8418. Min Act: -0.1700
Data Index: 7061342 (Open Web Text)
Max Activating Token Index: 556
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9355. Min Range: -5.9355
Max Act: 5.7793. Min Act: -0.1700
Data Index: 1125272 (Open Web Text)
Max Activating Token Index: 518
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9355. Min Range: -5.9355
Max Act: 5.8418. Min Act: -0.1700
Data Index: 3096304 (Open Web Text)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9355. Min Range: -5.9355
Max Act: 5.8105. Min Act: -0.1700
Data Index: 7381274 (Open Web Text)
Max Activating Token Index: 432
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9355. Min Range: -5.9355
Max Act: 5.7793. Min Act: -0.1700
Data Index: 4544261 (Open Web Text)
Max Activating Token Index: 915
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9355. Min Range: -5.9355
Max Act: 5.8105. Min Act: -0.1700
Data Index: 2088162 (Open Web Text)
Max Activating Token Index: 677
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9355. Min Range: -5.9355
Max Act: 5.8105. Min Act: -0.1698
Data Index: 7309119 (Open Web Text)
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9355. Min Range: -5.9355
Max Act: 5.7480. Min Act: -0.1700
Data Index: 1231756 (Open Web Text)
Max Activating Token Index: 847
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9355. Min Range: -5.9355
Max Act: 5.7480. Min Act: -0.1700
Data Index: 483476 (Open Web Text)
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9355. Min Range: -5.9355
Max Act: 5.7793. Min Act: -0.1694
Data Index: 5365704 (Open Web Text)
Max Activating Token Index: 124
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9355. Min Range: -5.9355
Max Act: 5.7793. Min Act: -0.1700
Data Index: 3457200 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9355. Min Range: -5.9355
Max Act: 5.7168. Min Act: -0.1700
Data Index: 3876830 (Open Web Text)
Max Activating Token Index: 997
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9355. Min Range: -5.9355
Max Act: 5.6855. Min Act: -0.1700
Data Index: 5150141 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9355. Min Range: -5.9355
Max Act: 5.7168. Min Act: -0.1698
Data Index: 8476440 (Open Web Text)
Max Activating Token Index: 111
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9355. Min Range: -5.9355
Max Act: 5.7168. Min Act: -0.1683
Data Index: 3024578 (Open Web Text)
Max Activating Token Index: 422
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9355. Min Range: -5.9355
Max Act: 5.7168. Min Act: -0.1700
Data Index: 5438023 (Open Web Text)
Max Activating Token Index: 397
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9355. Min Range: -5.9355
Max Act: 5.7168. Min Act: -0.1697
Data Index: 5797002 (Open Web Text)
Max Activating Token Index: 902
Click toggle to see full text
Truncated
Full Text #19