Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4954 in Layer 30
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.8218. Min Range: -4.8218
Max Act: 4.8218. Min Act: -0.1700
Data Index: 6075765 (Open Web Text)
Max Activating Token Index: 661
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.8218. Min Range: -4.8218
Max Act: 4.7593. Min Act: -0.1700
Data Index: 6174098 (Open Web Text)
Max Activating Token Index: 287
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.8218. Min Range: -4.8218
Max Act: 4.7593. Min Act: -0.1700
Data Index: 7819251 (Open Web Text)
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.8218. Min Range: -4.8218
Max Act: 4.7593. Min Act: -0.1700
Data Index: 7081958 (Open Web Text)
Max Activating Token Index: 363
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.8218. Min Range: -4.8218
Max Act: 4.7593. Min Act: -0.1700
Data Index: 5674073 (Open Web Text)
Max Activating Token Index: 432
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.8218. Min Range: -4.8218
Max Act: 4.7593. Min Act: -0.1700
Data Index: 7733059 (Open Web Text)
Max Activating Token Index: 315
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.8218. Min Range: -4.8218
Max Act: 4.7280. Min Act: -0.1700
Data Index: 6075764 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.8218. Min Range: -4.8218
Max Act: 4.7280. Min Act: -0.1700
Data Index: 931340 (Open Web Text)
Max Activating Token Index: 331
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.8218. Min Range: -4.8218
Max Act: 4.7280. Min Act: -0.1700
Data Index: 7733058 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.8218. Min Range: -4.8218
Max Act: 4.6968. Min Act: -0.1700
Data Index: 7734297 (Open Web Text)
Max Activating Token Index: 642
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.8218. Min Range: -4.8218
Max Act: 4.6968. Min Act: -0.1700
Data Index: 7818125 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.8218. Min Range: -4.8218
Max Act: 4.6655. Min Act: -0.1700
Data Index: 3200933 (Open Web Text)
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.8218. Min Range: -4.8218
Max Act: 4.6343. Min Act: -0.1700
Data Index: 931341 (Open Web Text)
Max Activating Token Index: 198
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.8218. Min Range: -4.8218
Max Act: 4.6343. Min Act: -0.1700
Data Index: 299745 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.8218. Min Range: -4.8218
Max Act: 4.6343. Min Act: -0.1700
Data Index: 3200931 (Open Web Text)
Max Activating Token Index: 916
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.8218. Min Range: -4.8218
Max Act: 4.6343. Min Act: -0.1700
Data Index: 7734299 (Open Web Text)
Max Activating Token Index: 337
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.8218. Min Range: -4.8218
Max Act: 4.5405. Min Act: -0.1700
Data Index: 5419295 (Open Web Text)
Max Activating Token Index: 421
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.8218. Min Range: -4.8218
Max Act: 4.4780. Min Act: -0.1700
Data Index: 197942 (Open Web Text)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.8218. Min Range: -4.8218
Max Act: 4.4468. Min Act: -0.1700
Data Index: 8518551 (Open Web Text)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.8218. Min Range: -4.8218
Max Act: 4.4468. Min Act: -0.1700
Data Index: 6914106 (Open Web Text)
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #19