Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3425 in Layer 11
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.6615. Min Range: -3.6615
Max Act: 3.6615. Min Act: -0.1700
Data Index: 6673547 (Open Web Text)
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.6615. Min Range: -3.6615
Max Act: 3.5833. Min Act: -0.1700
Data Index: 2994577 (Open Web Text)
Max Activating Token Index: 432
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.6615. Min Range: -3.6615
Max Act: 3.5520. Min Act: -0.1700
Data Index: 8693983 (Open Web Text)
Max Activating Token Index: 973
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.6615. Min Range: -3.6615
Max Act: 3.5363. Min Act: -0.1700
Data Index: 6339163 (Open Web Text)
Max Activating Token Index: 131
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.6615. Min Range: -3.6615
Max Act: 3.4736. Min Act: -0.1700
Data Index: 8782258 (Open Web Text)
Max Activating Token Index: 198
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.6615. Min Range: -3.6615
Max Act: 3.4580. Min Act: -0.1700
Data Index: 2401925 (Open Web Text)
Max Activating Token Index: 402
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.6615. Min Range: -3.6615
Max Act: 3.4266. Min Act: -0.1700
Data Index: 7168933 (Open Web Text)
Max Activating Token Index: 906
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.6615. Min Range: -3.6615
Max Act: 3.4423. Min Act: -0.1700
Data Index: 3206540 (Open Web Text)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.6615. Min Range: -3.6615
Max Act: 3.3953. Min Act: -0.1700
Data Index: 6981249 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.6615. Min Range: -3.6615
Max Act: 3.4110. Min Act: -0.1700
Data Index: 7042765 (Open Web Text)
Max Activating Token Index: 388
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.6615. Min Range: -3.6615
Max Act: 3.4110. Min Act: -0.1700
Data Index: 746579 (Open Web Text)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.6615. Min Range: -3.6615
Max Act: 3.4266. Min Act: -0.1700
Data Index: 7259272 (Open Web Text)
Max Activating Token Index: 918
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.6615. Min Range: -3.6615
Max Act: 3.3639. Min Act: -0.1700
Data Index: 6258425 (Open Web Text)
Max Activating Token Index: 167
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.6615. Min Range: -3.6615
Max Act: 3.3953. Min Act: -0.1700
Data Index: 3760813 (Open Web Text)
Max Activating Token Index: 543
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.6615. Min Range: -3.6615
Max Act: 3.3482. Min Act: -0.1700
Data Index: 7247237 (Open Web Text)
Max Activating Token Index: 305
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.6615. Min Range: -3.6615
Max Act: 3.3639. Min Act: -0.1700
Data Index: 523873 (Open Web Text)
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.6615. Min Range: -3.6615
Max Act: 3.3796. Min Act: -0.1700
Data Index: 6700336 (Open Web Text)
Max Activating Token Index: 829
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.6615. Min Range: -3.6615
Max Act: 3.3325. Min Act: -0.1700
Data Index: 543867 (Open Web Text)
Max Activating Token Index: 1003
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.6615. Min Range: -3.6615
Max Act: 3.3325. Min Act: -0.1700
Data Index: 3784137 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.6615. Min Range: -3.6615
Max Act: 3.3325. Min Act: -0.1700
Data Index: 3003905 (Open Web Text)
Max Activating Token Index: 400
Click toggle to see full text
Truncated
Full Text #19