Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3993 in Layer 12
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.3252. Min Range: -3.3252
Max Act: 3.3252. Min Act: -0.1700
Data Index: 2239219 (Open Web Text)
Max Activating Token Index: 241
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.3252. Min Range: -3.3252
Max Act: 3.1996. Min Act: -0.1700
Data Index: 5629604 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.3252. Min Range: -3.3252
Max Act: 3.1524. Min Act: -0.1700
Data Index: 4239593 (Open Web Text)
Max Activating Token Index: 977
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.3252. Min Range: -3.3252
Max Act: 3.1051. Min Act: -0.1700
Data Index: 1917992 (Open Web Text)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.3252. Min Range: -3.3252
Max Act: 3.0578. Min Act: -0.1700
Data Index: 2127851 (Open Web Text)
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.3252. Min Range: -3.3252
Max Act: 3.0736. Min Act: -0.1700
Data Index: 2211952 (Open Web Text)
Max Activating Token Index: 113
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.3252. Min Range: -3.3252
Max Act: 3.0578. Min Act: -0.1700
Data Index: 7120240 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.3252. Min Range: -3.3252
Max Act: 3.0420. Min Act: -0.1700
Data Index: 3671799 (Open Web Text)
Max Activating Token Index: 190
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.3252. Min Range: -3.3252
Max Act: 3.0420. Min Act: -0.1700
Data Index: 6014525 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.3252. Min Range: -3.3252
Max Act: 3.0262. Min Act: -0.1700
Data Index: 2482582 (Open Web Text)
Max Activating Token Index: 799
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.3252. Min Range: -3.3252
Max Act: 2.9946. Min Act: -0.1700
Data Index: 7849394 (Open Web Text)
Max Activating Token Index: 847
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.3252. Min Range: -3.3252
Max Act: 2.9788. Min Act: -0.1700
Data Index: 2160195 (Open Web Text)
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.3252. Min Range: -3.3252
Max Act: 2.9630. Min Act: -0.1700
Data Index: 1023918 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.3252. Min Range: -3.3252
Max Act: 2.9472. Min Act: -0.1700
Data Index: 1418899 (Open Web Text)
Max Activating Token Index: 1008
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.3252. Min Range: -3.3252
Max Act: 2.9472. Min Act: -0.1700
Data Index: 4058179 (Open Web Text)
Max Activating Token Index: 390
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.3252. Min Range: -3.3252
Max Act: 2.9314. Min Act: -0.1700
Data Index: 7857806 (Open Web Text)
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.3252. Min Range: -3.3252
Max Act: 2.9472. Min Act: -0.1700
Data Index: 4659391 (Open Web Text)
Max Activating Token Index: 483
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.3252. Min Range: -3.3252
Max Act: 2.9314. Min Act: -0.1700
Data Index: 7388965 (Open Web Text)
Max Activating Token Index: 242
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.3252. Min Range: -3.3252
Max Act: 2.9155. Min Act: -0.1700
Data Index: 5489136 (Open Web Text)
Max Activating Token Index: 704
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.3252. Min Range: -3.3252
Max Act: 2.8997. Min Act: -0.1700
Data Index: 5329712 (Open Web Text)
Max Activating Token Index: 287
Click toggle to see full text
Truncated
Full Text #19