Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1668 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 1.7102. Min Range: -1.7102
Max Act: 1.7015. Min Act: -0.1699
Data Index: 907610 (Open Web Text)
Max Activating Token Index: 257
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.7102. Min Range: -1.7102
Max Act: 1.7102. Min Act: -0.1700
Data Index: 7488426 (Open Web Text)
Max Activating Token Index: 185
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.7102. Min Range: -1.7102
Max Act: 1.6842. Min Act: -0.1700
Data Index: 2166187 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.7102. Min Range: -1.7102
Max Act: 1.6755. Min Act: -0.1699
Data Index: 4608296 (Open Web Text)
Max Activating Token Index: 205
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.7102. Min Range: -1.7102
Max Act: 1.6668. Min Act: -0.1700
Data Index: 6434411 (Open Web Text)
Max Activating Token Index: 222
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.7102. Min Range: -1.7102
Max Act: 1.6494. Min Act: -0.1700
Data Index: 135490 (Open Web Text)
Max Activating Token Index: 157
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.7102. Min Range: -1.7102
Max Act: 1.6407. Min Act: -0.1700
Data Index: 3543980 (Open Web Text)
Max Activating Token Index: 123
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.7102. Min Range: -1.7102
Max Act: 1.6407. Min Act: -0.1700
Data Index: 171973 (Open Web Text)
Max Activating Token Index: 247
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.7102. Min Range: -1.7102
Max Act: 1.6581. Min Act: -0.1700
Data Index: 4120429 (Open Web Text)
Max Activating Token Index: 216
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.7102. Min Range: -1.7102
Max Act: 1.6233. Min Act: -0.1699
Data Index: 4871951 (Open Web Text)
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.7102. Min Range: -1.7102
Max Act: 1.6320. Min Act: -0.1700
Data Index: 355873 (Open Web Text)
Max Activating Token Index: 174
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.7102. Min Range: -1.7102
Max Act: 1.6233. Min Act: -0.1700
Data Index: 8157871 (Open Web Text)
Max Activating Token Index: 81
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.7102. Min Range: -1.7102
Max Act: 1.6145. Min Act: -0.1699
Data Index: 2375333 (Open Web Text)
Max Activating Token Index: 129
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.7102. Min Range: -1.7102
Max Act: 1.6058. Min Act: -0.1700
Data Index: 656405 (Open Web Text)
Max Activating Token Index: 207
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.7102. Min Range: -1.7102
Max Act: 1.5971. Min Act: -0.1699
Data Index: 3611078 (Open Web Text)
Max Activating Token Index: 152
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.7102. Min Range: -1.7102
Max Act: 1.6058. Min Act: -0.1700
Data Index: 8350974 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.7102. Min Range: -1.7102
Max Act: 1.6058. Min Act: -0.1699
Data Index: 1412560 (Open Web Text)
Max Activating Token Index: 109
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.7102. Min Range: -1.7102
Max Act: 1.5971. Min Act: -0.1700
Data Index: 8606015 (Open Web Text)
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.7102. Min Range: -1.7102
Max Act: 1.6058. Min Act: -0.1700
Data Index: 7463857 (Open Web Text)
Max Activating Token Index: 137
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.7102. Min Range: -1.7102
Max Act: 1.6058. Min Act: -0.1700
Data Index: 6202742 (Open Web Text)
Max Activating Token Index: 220
Click toggle to see full text
Truncated
Full Text #19