Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 721 in Layer 9
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.5357. Min Range: -5.5357
Max Act: 5.5357. Min Act: -0.1700
Data Index: 6468925 (Open Web Text)
Max Activating Token Index: 277
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.5357. Min Range: -5.5357
Max Act: 5.4732. Min Act: -0.1700
Data Index: 8676788 (Open Web Text)
Max Activating Token Index: 365
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.5357. Min Range: -5.5357
Max Act: 5.4419. Min Act: -0.1700
Data Index: 6847821 (Open Web Text)
Max Activating Token Index: 86
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.5357. Min Range: -5.5357
Max Act: 5.2857. Min Act: -0.1700
Data Index: 7640822 (Open Web Text)
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.5357. Min Range: -5.5357
Max Act: 5.2857. Min Act: -0.1700
Data Index: 180315 (Open Web Text)
Max Activating Token Index: 252
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.5357. Min Range: -5.5357
Max Act: 5.2544. Min Act: -0.1700
Data Index: 4173169 (Open Web Text)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.5357. Min Range: -5.5357
Max Act: 5.2857. Min Act: -0.1700
Data Index: 1097750 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.5357. Min Range: -5.5357
Max Act: 5.2857. Min Act: -0.1700
Data Index: 5099697 (Open Web Text)
Max Activating Token Index: 716
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.5357. Min Range: -5.5357
Max Act: 5.2232. Min Act: -0.1700
Data Index: 1507700 (Open Web Text)
Max Activating Token Index: 501
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.5357. Min Range: -5.5357
Max Act: 5.2544. Min Act: -0.1700
Data Index: 442018 (Open Web Text)
Max Activating Token Index: 386
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.5357. Min Range: -5.5357
Max Act: 5.2544. Min Act: -0.1700
Data Index: 4487256 (Open Web Text)
Max Activating Token Index: 382
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.5357. Min Range: -5.5357
Max Act: 5.2544. Min Act: -0.1700
Data Index: 8457993 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.5357. Min Range: -5.5357
Max Act: 5.2232. Min Act: -0.1700
Data Index: 962541 (Open Web Text)
Max Activating Token Index: 718
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.5357. Min Range: -5.5357
Max Act: 5.2544. Min Act: -0.1700
Data Index: 543574 (Open Web Text)
Max Activating Token Index: 579
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.5357. Min Range: -5.5357
Max Act: 5.2232. Min Act: -0.1700
Data Index: 2525768 (Open Web Text)
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.5357. Min Range: -5.5357
Max Act: 5.1919. Min Act: -0.1700
Data Index: 473582 (Open Web Text)
Max Activating Token Index: 1000
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.5357. Min Range: -5.5357
Max Act: 5.1607. Min Act: -0.1700
Data Index: 3026609 (Open Web Text)
Max Activating Token Index: 323
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.5357. Min Range: -5.5357
Max Act: 5.1919. Min Act: -0.1700
Data Index: 1941418 (Open Web Text)
Max Activating Token Index: 461
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.5357. Min Range: -5.5357
Max Act: 5.1294. Min Act: -0.1700
Data Index: 5903307 (Open Web Text)
Max Activating Token Index: 909
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.5357. Min Range: -5.5357
Max Act: 5.0982. Min Act: -0.1700
Data Index: 5861912 (Open Web Text)
Max Activating Token Index: 237
Click toggle to see full text
Truncated
Full Text #19