Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2886 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.6226. Min Range: -4.6226
Max Act: 4.6226. Min Act: -0.1700
Data Index: 6850347 (Open Web Text)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.6226. Min Range: -4.6226
Max Act: 4.5601. Min Act: -0.1700
Data Index: 8038013 (Open Web Text)
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.6226. Min Range: -4.6226
Max Act: 4.5288. Min Act: -0.1700
Data Index: 1609088 (Open Web Text)
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.6226. Min Range: -4.6226
Max Act: 4.4976. Min Act: -0.1700
Data Index: 4388778 (Open Web Text)
Max Activating Token Index: 937
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.6226. Min Range: -4.6226
Max Act: 4.4663. Min Act: -0.1700
Data Index: 656080 (Open Web Text)
Max Activating Token Index: 515
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.6226. Min Range: -4.6226
Max Act: 4.4976. Min Act: -0.1700
Data Index: 4398585 (Open Web Text)
Max Activating Token Index: 603
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.6226. Min Range: -4.6226
Max Act: 4.4038. Min Act: -0.1700
Data Index: 1314316 (Open Web Text)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.6226. Min Range: -4.6226
Max Act: 4.4351. Min Act: -0.1700
Data Index: 4401109 (Open Web Text)
Max Activating Token Index: 924
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.6226. Min Range: -4.6226
Max Act: 4.4351. Min Act: -0.1700
Data Index: 1018039 (Open Web Text)
Max Activating Token Index: 910
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.6226. Min Range: -4.6226
Max Act: 4.4351. Min Act: -0.1700
Data Index: 4832715 (Open Web Text)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.6226. Min Range: -4.6226
Max Act: 4.3726. Min Act: -0.1700
Data Index: 2821867 (Open Web Text)
Max Activating Token Index: 376
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.6226. Min Range: -4.6226
Max Act: 4.4038. Min Act: -0.1700
Data Index: 6065773 (Open Web Text)
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.6226. Min Range: -4.6226
Max Act: 4.3726. Min Act: -0.1700
Data Index: 6358570 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.6226. Min Range: -4.6226
Max Act: 4.3413. Min Act: -0.1700
Data Index: 7132935 (Open Web Text)
Max Activating Token Index: 975
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.6226. Min Range: -4.6226
Max Act: 4.3101. Min Act: -0.1700
Data Index: 5458706 (Open Web Text)
Max Activating Token Index: 649
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.6226. Min Range: -4.6226
Max Act: 4.4038. Min Act: -0.1700
Data Index: 65599 (Open Web Text)
Max Activating Token Index: 459
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.6226. Min Range: -4.6226
Max Act: 4.4038. Min Act: -0.1700
Data Index: 4473888 (Open Web Text)
Max Activating Token Index: 422
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.6226. Min Range: -4.6226
Max Act: 4.3726. Min Act: -0.1700
Data Index: 4240760 (Open Web Text)
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.6226. Min Range: -4.6226
Max Act: 4.3413. Min Act: -0.1700
Data Index: 6353059 (Open Web Text)
Max Activating Token Index: 952
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.6226. Min Range: -4.6226
Max Act: 4.3726. Min Act: -0.1700
Data Index: 501023 (Open Web Text)
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #19