Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5937 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.6257. Min Range: -5.6257
Max Act: 5.6257. Min Act: -0.1700
Data Index: 6089288 (Open Web Text)
Max Activating Token Index: 291
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.6257. Min Range: -5.6257
Max Act: 5.4070. Min Act: -0.1700
Data Index: 8499813 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.6257. Min Range: -5.6257
Max Act: 5.3445. Min Act: -0.1700
Data Index: 6472090 (Open Web Text)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.6257. Min Range: -5.6257
Max Act: 5.3132. Min Act: -0.1700
Data Index: 8499810 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.6257. Min Range: -5.6257
Max Act: 5.2507. Min Act: -0.1700
Data Index: 6407902 (Open Web Text)
Max Activating Token Index: 506
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.6257. Min Range: -5.6257
Max Act: 5.2507. Min Act: -0.1700
Data Index: 6419383 (Open Web Text)
Max Activating Token Index: 326
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.6257. Min Range: -5.6257
Max Act: 5.2195. Min Act: -0.1700
Data Index: 2740099 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.6257. Min Range: -5.6257
Max Act: 5.2507. Min Act: -0.1700
Data Index: 6947813 (Open Web Text)
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.6257. Min Range: -5.6257
Max Act: 5.1882. Min Act: -0.1700
Data Index: 5151442 (Open Web Text)
Max Activating Token Index: 1005
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.6257. Min Range: -5.6257
Max Act: 5.1882. Min Act: -0.1700
Data Index: 2740097 (Open Web Text)
Max Activating Token Index: 876
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.6257. Min Range: -5.6257
Max Act: 5.1882. Min Act: -0.1700
Data Index: 1453256 (Open Web Text)
Max Activating Token Index: 876
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.6257. Min Range: -5.6257
Max Act: 5.1882. Min Act: -0.1700
Data Index: 6176986 (Open Web Text)
Max Activating Token Index: 997
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.6257. Min Range: -5.6257
Max Act: 5.1882. Min Act: -0.1700
Data Index: 7160443 (Open Web Text)
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.6257. Min Range: -5.6257
Max Act: 5.1570. Min Act: -0.1697
Data Index: 7618379 (Open Web Text)
Max Activating Token Index: 795
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.6257. Min Range: -5.6257
Max Act: 5.1570. Min Act: -0.1700
Data Index: 5164810 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.6257. Min Range: -5.6257
Max Act: 5.1257. Min Act: -0.1700
Data Index: 8499814 (Open Web Text)
Max Activating Token Index: 501
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.6257. Min Range: -5.6257
Max Act: 5.1570. Min Act: -0.1700
Data Index: 8499809 (Open Web Text)
Max Activating Token Index: 979
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.6257. Min Range: -5.6257
Max Act: 5.0945. Min Act: -0.1700
Data Index: 4381999 (Open Web Text)
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.6257. Min Range: -5.6257
Max Act: 5.0945. Min Act: -0.1700
Data Index: 420536 (Open Web Text)
Max Activating Token Index: 250
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.6257. Min Range: -5.6257
Max Act: 5.1570. Min Act: -0.1700
Data Index: 8648314 (Open Web Text)
Max Activating Token Index: 141
Click toggle to see full text
Truncated
Full Text #19