Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 56 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.7807. Min Range: -4.7807
Max Act: 4.7807. Min Act: -0.1700
Data Index: 334958 (Open Web Text)
Max Activating Token Index: 432
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.7807. Min Range: -4.7807
Max Act: 4.6557. Min Act: -0.1700
Data Index: 3306482 (Open Web Text)
Max Activating Token Index: 929
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.7807. Min Range: -4.7807
Max Act: 4.6557. Min Act: -0.1700
Data Index: 2566637 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.7807. Min Range: -4.7807
Max Act: 4.6244. Min Act: -0.1700
Data Index: 3461854 (Open Web Text)
Max Activating Token Index: 352
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.7807. Min Range: -4.7807
Max Act: 4.5932. Min Act: -0.1700
Data Index: 7875740 (Open Web Text)
Max Activating Token Index: 925
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.7807. Min Range: -4.7807
Max Act: 4.5619. Min Act: -0.1700
Data Index: 6649610 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.7807. Min Range: -4.7807
Max Act: 4.5307. Min Act: -0.1700
Data Index: 3771668 (Open Web Text)
Max Activating Token Index: 359
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.7807. Min Range: -4.7807
Max Act: 4.5619. Min Act: -0.1700
Data Index: 1544665 (Open Web Text)
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.7807. Min Range: -4.7807
Max Act: 4.5307. Min Act: -0.1700
Data Index: 6771329 (Open Web Text)
Max Activating Token Index: 999
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.7807. Min Range: -4.7807
Max Act: 4.5619. Min Act: -0.1700
Data Index: 371189 (Open Web Text)
Max Activating Token Index: 924
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.7807. Min Range: -4.7807
Max Act: 4.5619. Min Act: -0.1700
Data Index: 5585840 (Open Web Text)
Max Activating Token Index: 518
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.7807. Min Range: -4.7807
Max Act: 4.5307. Min Act: -0.1700
Data Index: 2863445 (Open Web Text)
Max Activating Token Index: 434
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.7807. Min Range: -4.7807
Max Act: 4.4994. Min Act: -0.1700
Data Index: 6074290 (Open Web Text)
Max Activating Token Index: 282
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.7807. Min Range: -4.7807
Max Act: 4.5307. Min Act: -0.1700
Data Index: 5493651 (Open Web Text)
Max Activating Token Index: 233
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.7807. Min Range: -4.7807
Max Act: 4.5307. Min Act: -0.1700
Data Index: 4444633 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.7807. Min Range: -4.7807
Max Act: 4.5307. Min Act: -0.1700
Data Index: 4806085 (Open Web Text)
Max Activating Token Index: 246
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.7807. Min Range: -4.7807
Max Act: 4.5307. Min Act: -0.1700
Data Index: 7967091 (Open Web Text)
Max Activating Token Index: 1018
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.7807. Min Range: -4.7807
Max Act: 4.5307. Min Act: -0.1700
Data Index: 5571010 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.7807. Min Range: -4.7807
Max Act: 4.5307. Min Act: -0.1700
Data Index: 4346173 (Open Web Text)
Max Activating Token Index: 52
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.7807. Min Range: -4.7807
Max Act: 4.4994. Min Act: -0.1700
Data Index: 6711487 (Open Web Text)
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #19