Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 606 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 6.1233. Min Range: -6.1233
Max Act: 6.1233. Min Act: -0.1700
Data Index: 131707 (Open Web Text)
Max Activating Token Index: 163
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.1233. Min Range: -6.1233
Max Act: 5.9983. Min Act: -0.1700
Data Index: 923799 (Open Web Text)
Max Activating Token Index: 167
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.1233. Min Range: -6.1233
Max Act: 5.9671. Min Act: -0.1700
Data Index: 4379597 (Open Web Text)
Max Activating Token Index: 93
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.1233. Min Range: -6.1233
Max Act: 5.9358. Min Act: -0.1700
Data Index: 7694753 (Open Web Text)
Max Activating Token Index: 79
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.1233. Min Range: -6.1233
Max Act: 5.9046. Min Act: -0.1700
Data Index: 143876 (Open Web Text)
Max Activating Token Index: 129
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.1233. Min Range: -6.1233
Max Act: 5.9046. Min Act: -0.1700
Data Index: 3916227 (Open Web Text)
Max Activating Token Index: 941
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.1233. Min Range: -6.1233
Max Act: 5.8733. Min Act: -0.1700
Data Index: 1241780 (Open Web Text)
Max Activating Token Index: 185
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.1233. Min Range: -6.1233
Max Act: 5.8733. Min Act: -0.1700
Data Index: 8135834 (Open Web Text)
Max Activating Token Index: 104
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.1233. Min Range: -6.1233
Max Act: 5.8733. Min Act: -0.1700
Data Index: 6171256 (Open Web Text)
Max Activating Token Index: 331
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.1233. Min Range: -6.1233
Max Act: 5.8733. Min Act: -0.1700
Data Index: 3352581 (Open Web Text)
Max Activating Token Index: 99
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.1233. Min Range: -6.1233
Max Act: 5.8421. Min Act: -0.1700
Data Index: 6697100 (Open Web Text)
Max Activating Token Index: 142
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.1233. Min Range: -6.1233
Max Act: 5.8733. Min Act: -0.1700
Data Index: 7125334 (Open Web Text)
Max Activating Token Index: 151
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.1233. Min Range: -6.1233
Max Act: 5.8421. Min Act: -0.1700
Data Index: 3224739 (Open Web Text)
Max Activating Token Index: 91
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.1233. Min Range: -6.1233
Max Act: 5.8108. Min Act: -0.1700
Data Index: 2342686 (Open Web Text)
Max Activating Token Index: 198
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.1233. Min Range: -6.1233
Max Act: 5.8108. Min Act: -0.1700
Data Index: 6232242 (Open Web Text)
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.1233. Min Range: -6.1233
Max Act: 5.8108. Min Act: -0.1700
Data Index: 8580251 (Open Web Text)
Max Activating Token Index: 166
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.1233. Min Range: -6.1233
Max Act: 5.8108. Min Act: -0.1700
Data Index: 4305800 (Open Web Text)
Max Activating Token Index: 158
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.1233. Min Range: -6.1233
Max Act: 5.7796. Min Act: -0.1700
Data Index: 7254793 (Open Web Text)
Max Activating Token Index: 141
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.1233. Min Range: -6.1233
Max Act: 5.7796. Min Act: -0.1700
Data Index: 3824114 (Open Web Text)
Max Activating Token Index: 53
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.1233. Min Range: -6.1233
Max Act: 5.7796. Min Act: -0.1700
Data Index: 8250490 (Open Web Text)
Max Activating Token Index: 92
Click toggle to see full text
Truncated
Full Text #19