Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5700 in Layer 6
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.0020. Min Range: -4.0020
Max Act: 4.0020. Min Act: -0.1700
Data Index: 744038 (Open Web Text)
Max Activating Token Index: 265
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.0020. Min Range: -4.0020
Max Act: 3.9708. Min Act: -0.1700
Data Index: 4827016 (Open Web Text)
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.0020. Min Range: -4.0020
Max Act: 3.9708. Min Act: -0.1700
Data Index: 8275428 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.0020. Min Range: -4.0020
Max Act: 3.9708. Min Act: -0.1700
Data Index: 2172758 (Open Web Text)
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.0020. Min Range: -4.0020
Max Act: 3.9395. Min Act: -0.1700
Data Index: 1758443 (Open Web Text)
Max Activating Token Index: 70
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.0020. Min Range: -4.0020
Max Act: 3.9395. Min Act: -0.1700
Data Index: 1355633 (Open Web Text)
Max Activating Token Index: 687
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.0020. Min Range: -4.0020
Max Act: 3.9395. Min Act: -0.1700
Data Index: 2102512 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.0020. Min Range: -4.0020
Max Act: 3.9708. Min Act: -0.1700
Data Index: 8658214 (Open Web Text)
Max Activating Token Index: 222
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.0020. Min Range: -4.0020
Max Act: 3.8770. Min Act: -0.1700
Data Index: 7092536 (Open Web Text)
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.0020. Min Range: -4.0020
Max Act: 3.8457. Min Act: -0.1700
Data Index: 2998710 (Open Web Text)
Max Activating Token Index: 653
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.0020. Min Range: -4.0020
Max Act: 3.8770. Min Act: -0.1700
Data Index: 3753201 (Open Web Text)
Max Activating Token Index: 282
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.0020. Min Range: -4.0020
Max Act: 3.8457. Min Act: -0.1700
Data Index: 6906239 (Open Web Text)
Max Activating Token Index: 841
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.0020. Min Range: -4.0020
Max Act: 3.8457. Min Act: -0.1700
Data Index: 3732356 (Open Web Text)
Max Activating Token Index: 590
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.0020. Min Range: -4.0020
Max Act: 3.8144. Min Act: -0.1700
Data Index: 1660793 (Open Web Text)
Max Activating Token Index: 204
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.0020. Min Range: -4.0020
Max Act: 3.8144. Min Act: -0.1700
Data Index: 6507557 (Open Web Text)
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.0020. Min Range: -4.0020
Max Act: 3.8144. Min Act: -0.1700
Data Index: 6204506 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.0020. Min Range: -4.0020
Max Act: 3.8144. Min Act: -0.1700
Data Index: 8429973 (Open Web Text)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.0020. Min Range: -4.0020
Max Act: 3.7831. Min Act: -0.1700
Data Index: 4012740 (Open Web Text)
Max Activating Token Index: 969
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.0020. Min Range: -4.0020
Max Act: 3.7831. Min Act: -0.1700
Data Index: 1432808 (Open Web Text)
Max Activating Token Index: 359
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.0020. Min Range: -4.0020
Max Act: 3.7519. Min Act: -0.1700
Data Index: 1415366 (Open Web Text)
Max Activating Token Index: 747
Click toggle to see full text
Truncated
Full Text #19