Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3980 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.5446. Min Range: -4.5446
Max Act: 4.5446. Min Act: -0.1700
Data Index: 6882328 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.5446. Min Range: -4.5446
Max Act: 4.4821. Min Act: -0.1700
Data Index: 3366503 (Open Web Text)
Max Activating Token Index: 391
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.5446. Min Range: -4.5446
Max Act: 4.3258. Min Act: -0.1700
Data Index: 4244615 (Open Web Text)
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.5446. Min Range: -4.5446
Max Act: 4.2633. Min Act: -0.1700
Data Index: 7027040 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.5446. Min Range: -4.5446
Max Act: 4.2633. Min Act: -0.1700
Data Index: 6956390 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.5446. Min Range: -4.5446
Max Act: 4.2633. Min Act: -0.1700
Data Index: 3031014 (Open Web Text)
Max Activating Token Index: 463
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.5446. Min Range: -4.5446
Max Act: 4.2321. Min Act: -0.1700
Data Index: 3701195 (Open Web Text)
Max Activating Token Index: 329
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.5446. Min Range: -4.5446
Max Act: 4.2633. Min Act: -0.1700
Data Index: 2795200 (Open Web Text)
Max Activating Token Index: 732
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.5446. Min Range: -4.5446
Max Act: 4.2321. Min Act: -0.1700
Data Index: 1105105 (Open Web Text)
Max Activating Token Index: 304
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.5446. Min Range: -4.5446
Max Act: 4.2321. Min Act: -0.1700
Data Index: 5869335 (Open Web Text)
Max Activating Token Index: 25
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.5446. Min Range: -4.5446
Max Act: 4.2008. Min Act: -0.1700
Data Index: 904290 (Open Web Text)
Max Activating Token Index: 201
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.5446. Min Range: -4.5446
Max Act: 4.2008. Min Act: -0.1700
Data Index: 8704366 (Open Web Text)
Max Activating Token Index: 363
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.5446. Min Range: -4.5446
Max Act: 4.1696. Min Act: -0.1700
Data Index: 5770715 (Open Web Text)
Max Activating Token Index: 842
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.5446. Min Range: -4.5446
Max Act: 4.1696. Min Act: -0.1700
Data Index: 2694086 (Open Web Text)
Max Activating Token Index: 705
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.5446. Min Range: -4.5446
Max Act: 4.2008. Min Act: -0.1700
Data Index: 2521853 (Open Web Text)
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.5446. Min Range: -4.5446
Max Act: 4.1696. Min Act: -0.1700
Data Index: 6638320 (Open Web Text)
Max Activating Token Index: 73
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.5446. Min Range: -4.5446
Max Act: 4.2008. Min Act: -0.1700
Data Index: 5594825 (Open Web Text)
Max Activating Token Index: 129
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.5446. Min Range: -4.5446
Max Act: 4.1383. Min Act: -0.1700
Data Index: 6833994 (Open Web Text)
Max Activating Token Index: 904
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.5446. Min Range: -4.5446
Max Act: 4.1383. Min Act: -0.1700
Data Index: 3231125 (Open Web Text)
Max Activating Token Index: 189
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.5446. Min Range: -4.5446
Max Act: 4.1383. Min Act: -0.1700
Data Index: 5983877 (Open Web Text)
Max Activating Token Index: 971
Click toggle to see full text
Truncated
Full Text #19