Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 37 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 2.0372. Min Range: -2.0372
Max Act: 2.0372. Min Act: -0.1700
Data Index: 5058888 (Open Web Text)
Max Activating Token Index: 581
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.0372. Min Range: -2.0372
Max Act: 2.0372. Min Act: -0.1700
Data Index: 3656261 (Open Web Text)
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.0372. Min Range: -2.0372
Max Act: 2.0204. Min Act: -0.1700
Data Index: 1786541 (Open Web Text)
Max Activating Token Index: 117
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.0372. Min Range: -2.0372
Max Act: 2.0035. Min Act: -0.1700
Data Index: 6653701 (Open Web Text)
Max Activating Token Index: 61
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.0372. Min Range: -2.0372
Max Act: 1.9866. Min Act: -0.1700
Data Index: 6730860 (Open Web Text)
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.0372. Min Range: -2.0372
Max Act: 1.9697. Min Act: -0.1700
Data Index: 4914469 (Open Web Text)
Max Activating Token Index: 57
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.0372. Min Range: -2.0372
Max Act: 1.9697. Min Act: -0.1700
Data Index: 2179334 (Open Web Text)
Max Activating Token Index: 183
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.0372. Min Range: -2.0372
Max Act: 1.9527. Min Act: -0.1700
Data Index: 5598827 (Open Web Text)
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.0372. Min Range: -2.0372
Max Act: 1.9697. Min Act: -0.1700
Data Index: 957904 (Open Web Text)
Max Activating Token Index: 138
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.0372. Min Range: -2.0372
Max Act: 1.9357. Min Act: -0.1700
Data Index: 5749281 (Open Web Text)
Max Activating Token Index: 848
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.0372. Min Range: -2.0372
Max Act: 1.9527. Min Act: -0.1700
Data Index: 6400801 (Open Web Text)
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.0372. Min Range: -2.0372
Max Act: 1.9527. Min Act: -0.1700
Data Index: 4628838 (Open Web Text)
Max Activating Token Index: 127
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.0372. Min Range: -2.0372
Max Act: 1.9187. Min Act: -0.1700
Data Index: 104614 (Open Web Text)
Max Activating Token Index: 197
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.0372. Min Range: -2.0372
Max Act: 1.9187. Min Act: -0.1700
Data Index: 1911945 (Open Web Text)
Max Activating Token Index: 1009
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.0372. Min Range: -2.0372
Max Act: 1.9357. Min Act: -0.1700
Data Index: 3096086 (Open Web Text)
Max Activating Token Index: 46
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.0372. Min Range: -2.0372
Max Act: 1.9357. Min Act: -0.1700
Data Index: 3203723 (Open Web Text)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.0372. Min Range: -2.0372
Max Act: 1.9357. Min Act: -0.1700
Data Index: 3698360 (Open Web Text)
Max Activating Token Index: 91
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.0372. Min Range: -2.0372
Max Act: 1.9357. Min Act: -0.1700
Data Index: 5070286 (Open Web Text)
Max Activating Token Index: 972
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.0372. Min Range: -2.0372
Max Act: 1.9357. Min Act: -0.1700
Data Index: 6459207 (Open Web Text)
Max Activating Token Index: 1016
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.0372. Min Range: -2.0372
Max Act: 1.9357. Min Act: -0.1700
Data Index: 4490752 (Open Web Text)
Max Activating Token Index: 388
Click toggle to see full text
Truncated
Full Text #19