Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 4063 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 1.9129. Min Range: -1.9129
Max Act: 1.9129. Min Act: -0.1700
Data Index: 2020088 (Open Web Text)
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.9129. Min Range: -1.9129
Max Act: 1.8445. Min Act: -0.1700
Data Index: 1796088 (Open Web Text)
Max Activating Token Index: 160
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.9129. Min Range: -1.9129
Max Act: 1.8274. Min Act: -0.1700
Data Index: 3530928 (Open Web Text)
Max Activating Token Index: 111
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.9129. Min Range: -1.9129
Max Act: 1.7844. Min Act: -0.1700
Data Index: 7139673 (Open Web Text)
Max Activating Token Index: 152
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.9129. Min Range: -1.9129
Max Act: 1.7758. Min Act: -0.1700
Data Index: 4822438 (Open Web Text)
Max Activating Token Index: 202
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.9129. Min Range: -1.9129
Max Act: 1.7585. Min Act: -0.1700
Data Index: 2405258 (Open Web Text)
Max Activating Token Index: 152
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.9129. Min Range: -1.9129
Max Act: 1.7585. Min Act: -0.1700
Data Index: 160933 (Open Web Text)
Max Activating Token Index: 74
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.9129. Min Range: -1.9129
Max Act: 1.7499. Min Act: -0.1700
Data Index: 8658995 (Open Web Text)
Max Activating Token Index: 143
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.9129. Min Range: -1.9129
Max Act: 1.7412. Min Act: -0.1700
Data Index: 3401132 (Open Web Text)
Max Activating Token Index: 197
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.9129. Min Range: -1.9129
Max Act: 1.7326. Min Act: -0.1700
Data Index: 2925737 (Open Web Text)
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.9129. Min Range: -1.9129
Max Act: 1.7326. Min Act: -0.1700
Data Index: 1796064 (Open Web Text)
Max Activating Token Index: 986
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.9129. Min Range: -1.9129
Max Act: 1.7239. Min Act: -0.1700
Data Index: 7614676 (Open Web Text)
Max Activating Token Index: 237
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.9129. Min Range: -1.9129
Max Act: 1.7239. Min Act: -0.1700
Data Index: 7846247 (Open Web Text)
Max Activating Token Index: 173
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.9129. Min Range: -1.9129
Max Act: 1.7239. Min Act: -0.1700
Data Index: 6898039 (Open Web Text)
Max Activating Token Index: 154
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.9129. Min Range: -1.9129
Max Act: 1.7239. Min Act: -0.1700
Data Index: 2687216 (Open Web Text)
Max Activating Token Index: 182
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.9129. Min Range: -1.9129
Max Act: 1.7066. Min Act: -0.1700
Data Index: 6610998 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.9129. Min Range: -1.9129
Max Act: 1.7153. Min Act: -0.1700
Data Index: 2506127 (Open Web Text)
Max Activating Token Index: 579
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.9129. Min Range: -1.9129
Max Act: 1.7153. Min Act: -0.1700
Data Index: 872729 (Open Web Text)
Max Activating Token Index: 58
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.9129. Min Range: -1.9129
Max Act: 1.7153. Min Act: -0.1700
Data Index: 904283 (Open Web Text)
Max Activating Token Index: 58
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.9129. Min Range: -1.9129
Max Act: 1.7066. Min Act: -0.1700
Data Index: 1419333 (Open Web Text)
Max Activating Token Index: 137
Click toggle to see full text
Truncated
Full Text #19