Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 4056 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 10.2486. Min Range: -10.2486
Max Act: 10.2486. Min Act: -0.1700
Data Index: 1821141 (Open Web Text)
Max Activating Token Index: 64
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 10.2486. Min Range: -10.2486
Max Act: 10.0611. Min Act: -0.1700
Data Index: 929012 (Open Web Text)
Max Activating Token Index: 173
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 10.2486. Min Range: -10.2486
Max Act: 10.1236. Min Act: -0.1700
Data Index: 4815781 (Open Web Text)
Max Activating Token Index: 516
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 10.2486. Min Range: -10.2486
Max Act: 9.9986. Min Act: -0.1700
Data Index: 3423866 (Open Web Text)
Max Activating Token Index: 854
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 10.2486. Min Range: -10.2486
Max Act: 9.9361. Min Act: -0.1700
Data Index: 2364511 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 10.2486. Min Range: -10.2486
Max Act: 9.8111. Min Act: -0.1700
Data Index: 8456189 (Open Web Text)
Max Activating Token Index: 731
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 10.2486. Min Range: -10.2486
Max Act: 9.9986. Min Act: -0.1700
Data Index: 5220182 (Open Web Text)
Max Activating Token Index: 501
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 10.2486. Min Range: -10.2486
Max Act: 9.8736. Min Act: -0.1700
Data Index: 8610997 (Open Web Text)
Max Activating Token Index: 310
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 10.2486. Min Range: -10.2486
Max Act: 9.7486. Min Act: -0.1700
Data Index: 986559 (Open Web Text)
Max Activating Token Index: 975
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 10.2486. Min Range: -10.2486
Max Act: 9.6861. Min Act: -0.1700
Data Index: 2986356 (Open Web Text)
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 10.2486. Min Range: -10.2486
Max Act: 9.6861. Min Act: -0.1700
Data Index: 3598529 (Open Web Text)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 10.2486. Min Range: -10.2486
Max Act: 9.7486. Min Act: -0.1700
Data Index: 4759497 (Open Web Text)
Max Activating Token Index: 369
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 10.2486. Min Range: -10.2486
Max Act: 9.7486. Min Act: -0.1700
Data Index: 5508848 (Open Web Text)
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 10.2486. Min Range: -10.2486
Max Act: 9.6236. Min Act: -0.1700
Data Index: 4660310 (Open Web Text)
Max Activating Token Index: 166
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 10.2486. Min Range: -10.2486
Max Act: 9.6236. Min Act: -0.1700
Data Index: 3855291 (Open Web Text)
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 10.2486. Min Range: -10.2486
Max Act: 9.5611. Min Act: -0.1700
Data Index: 2622101 (Open Web Text)
Max Activating Token Index: 898
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 10.2486. Min Range: -10.2486
Max Act: 9.5611. Min Act: -0.1700
Data Index: 6109855 (Open Web Text)
Max Activating Token Index: 297
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 10.2486. Min Range: -10.2486
Max Act: 9.6236. Min Act: -0.1700
Data Index: 358353 (Open Web Text)
Max Activating Token Index: 916
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 10.2486. Min Range: -10.2486
Max Act: 9.6236. Min Act: -0.1700
Data Index: 2326965 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 10.2486. Min Range: -10.2486
Max Act: 9.6236. Min Act: -0.1700
Data Index: 3313360 (Open Web Text)
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #19