Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3056 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 2.2186. Min Range: -2.2186
Max Act: 2.2186. Min Act: -0.1700
Data Index: 6108133 (Open Web Text)
Max Activating Token Index: 93
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.2186. Min Range: -2.2186
Max Act: 2.2020. Min Act: -0.1700
Data Index: 2659294 (Open Web Text)
Max Activating Token Index: 72
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.2186. Min Range: -2.2186
Max Act: 2.2186. Min Act: -0.1700
Data Index: 7919382 (Open Web Text)
Max Activating Token Index: 984
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.2186. Min Range: -2.2186
Max Act: 2.1854. Min Act: -0.1700
Data Index: 8133636 (Open Web Text)
Max Activating Token Index: 63
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.2186. Min Range: -2.2186
Max Act: 2.1688. Min Act: -0.1700
Data Index: 8787883 (Open Web Text)
Max Activating Token Index: 955
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.2186. Min Range: -2.2186
Max Act: 2.1355. Min Act: -0.1700
Data Index: 3933908 (Open Web Text)
Max Activating Token Index: 72
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.2186. Min Range: -2.2186
Max Act: 2.1521. Min Act: -0.1700
Data Index: 5261308 (Open Web Text)
Max Activating Token Index: 143
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.2186. Min Range: -2.2186
Max Act: 2.1355. Min Act: -0.1700
Data Index: 6669861 (Open Web Text)
Max Activating Token Index: 343
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.2186. Min Range: -2.2186
Max Act: 2.1355. Min Act: -0.1700
Data Index: 3018697 (Open Web Text)
Max Activating Token Index: 188
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.2186. Min Range: -2.2186
Max Act: 2.1188. Min Act: -0.1700
Data Index: 2978408 (Open Web Text)
Max Activating Token Index: 158
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.2186. Min Range: -2.2186
Max Act: 2.1188. Min Act: -0.1700
Data Index: 8508317 (Open Web Text)
Max Activating Token Index: 974
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.2186. Min Range: -2.2186
Max Act: 2.1020. Min Act: -0.1700
Data Index: 6558178 (Open Web Text)
Max Activating Token Index: 169
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.2186. Min Range: -2.2186
Max Act: 2.1020. Min Act: -0.1700
Data Index: 4923800 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.2186. Min Range: -2.2186
Max Act: 2.1188. Min Act: -0.1700
Data Index: 8815380 (Open Web Text)
Max Activating Token Index: 118
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.2186. Min Range: -2.2186
Max Act: 2.1020. Min Act: -0.1700
Data Index: 6864575 (Open Web Text)
Max Activating Token Index: 919
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.2186. Min Range: -2.2186
Max Act: 2.1020. Min Act: -0.1700
Data Index: 6772506 (Open Web Text)
Max Activating Token Index: 157
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.2186. Min Range: -2.2186
Max Act: 2.1020. Min Act: -0.1700
Data Index: 5937526 (Open Web Text)
Max Activating Token Index: 1017
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.2186. Min Range: -2.2186
Max Act: 2.1020. Min Act: -0.1700
Data Index: 1705524 (Open Web Text)
Max Activating Token Index: 484
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.2186. Min Range: -2.2186
Max Act: 2.0685. Min Act: -0.1700
Data Index: 1331201 (Open Web Text)
Max Activating Token Index: 125
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.2186. Min Range: -2.2186
Max Act: 2.0853. Min Act: -0.1700
Data Index: 7512848 (Open Web Text)
Max Activating Token Index: 216
Click toggle to see full text
Truncated
Full Text #19