Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3835 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.4916. Min Range: -3.4916
Max Act: 3.4916. Min Act: -0.1700
Data Index: 4785216 (Open Web Text)
Max Activating Token Index: 231
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.4916. Min Range: -3.4916
Max Act: 3.4916. Min Act: -0.1700
Data Index: 209935 (Open Web Text)
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.4916. Min Range: -3.4916
Max Act: 3.4446. Min Act: -0.1700
Data Index: 4013594 (Open Web Text)
Max Activating Token Index: 218
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.4916. Min Range: -3.4916
Max Act: 3.4133. Min Act: -0.1700
Data Index: 8113401 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.4916. Min Range: -3.4916
Max Act: 3.4289. Min Act: -0.1700
Data Index: 6604062 (Open Web Text)
Max Activating Token Index: 347
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.4916. Min Range: -3.4916
Max Act: 3.4289. Min Act: -0.1700
Data Index: 6428241 (Open Web Text)
Max Activating Token Index: 151
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.4916. Min Range: -3.4916
Max Act: 3.4759. Min Act: -0.1700
Data Index: 2732466 (Open Web Text)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.4916. Min Range: -3.4916
Max Act: 3.3976. Min Act: -0.1700
Data Index: 7443723 (Open Web Text)
Max Activating Token Index: 127
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.4916. Min Range: -3.4916
Max Act: 3.3819. Min Act: -0.1700
Data Index: 5800502 (Open Web Text)
Max Activating Token Index: 20
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.4916. Min Range: -3.4916
Max Act: 3.3348. Min Act: -0.1700
Data Index: 4277549 (Open Web Text)
Max Activating Token Index: 187
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.4916. Min Range: -3.4916
Max Act: 3.3662. Min Act: -0.1700
Data Index: 7066541 (Open Web Text)
Max Activating Token Index: 120
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.4916. Min Range: -3.4916
Max Act: 3.3505. Min Act: -0.1700
Data Index: 2071818 (Open Web Text)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.4916. Min Range: -3.4916
Max Act: 3.3662. Min Act: -0.1700
Data Index: 3724744 (Open Web Text)
Max Activating Token Index: 695
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.4916. Min Range: -3.4916
Max Act: 3.3348. Min Act: -0.1700
Data Index: 2214578 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.4916. Min Range: -3.4916
Max Act: 3.3348. Min Act: -0.1700
Data Index: 6851832 (Open Web Text)
Max Activating Token Index: 972
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.4916. Min Range: -3.4916
Max Act: 3.3035. Min Act: -0.1700
Data Index: 3982766 (Open Web Text)
Max Activating Token Index: 933
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.4916. Min Range: -3.4916
Max Act: 3.2406. Min Act: -0.1700
Data Index: 5527804 (Open Web Text)
Max Activating Token Index: 295
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.4916. Min Range: -3.4916
Max Act: 3.3348. Min Act: -0.1700
Data Index: 6771093 (Open Web Text)
Max Activating Token Index: 543
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.4916. Min Range: -3.4916
Max Act: 3.3192. Min Act: -0.1700
Data Index: 3385529 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.4916. Min Range: -3.4916
Max Act: 3.2721. Min Act: -0.1700
Data Index: 3971587 (Open Web Text)
Max Activating Token Index: 728
Click toggle to see full text
Truncated
Full Text #19