Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 652 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.3083. Min Range: -5.3083
Max Act: 5.3083. Min Act: -0.1700
Data Index: 1944602 (Open Web Text)
Max Activating Token Index: 172
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.3083. Min Range: -5.3083
Max Act: 5.3083. Min Act: -0.1700
Data Index: 6349756 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.3083. Min Range: -5.3083
Max Act: 5.2771. Min Act: -0.1700
Data Index: 4322042 (Open Web Text)
Max Activating Token Index: 213
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.3083. Min Range: -5.3083
Max Act: 5.2458. Min Act: -0.1700
Data Index: 4569985 (Open Web Text)
Max Activating Token Index: 263
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.3083. Min Range: -5.3083
Max Act: 5.3083. Min Act: -0.1700
Data Index: 577462 (Open Web Text)
Max Activating Token Index: 79
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.3083. Min Range: -5.3083
Max Act: 5.2458. Min Act: -0.1700
Data Index: 2597484 (Open Web Text)
Max Activating Token Index: 171
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.3083. Min Range: -5.3083
Max Act: 5.2146. Min Act: -0.1700
Data Index: 3239401 (Open Web Text)
Max Activating Token Index: 175
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.3083. Min Range: -5.3083
Max Act: 5.2146. Min Act: -0.1700
Data Index: 6822611 (Open Web Text)
Max Activating Token Index: 246
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.3083. Min Range: -5.3083
Max Act: 5.2146. Min Act: -0.1700
Data Index: 5630199 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.3083. Min Range: -5.3083
Max Act: 5.2146. Min Act: -0.1700
Data Index: 6132847 (Open Web Text)
Max Activating Token Index: 49
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.3083. Min Range: -5.3083
Max Act: 5.1833. Min Act: -0.1700
Data Index: 6938613 (Open Web Text)
Max Activating Token Index: 85
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.3083. Min Range: -5.3083
Max Act: 5.1833. Min Act: -0.1700
Data Index: 5741174 (Open Web Text)
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.3083. Min Range: -5.3083
Max Act: 5.1833. Min Act: -0.1700
Data Index: 7371186 (Open Web Text)
Max Activating Token Index: 48
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.3083. Min Range: -5.3083
Max Act: 5.1521. Min Act: -0.1700
Data Index: 4598777 (Open Web Text)
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.3083. Min Range: -5.3083
Max Act: 5.1208. Min Act: -0.1700
Data Index: 806318 (Open Web Text)
Max Activating Token Index: 59
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.3083. Min Range: -5.3083
Max Act: 5.1521. Min Act: -0.1700
Data Index: 7233070 (Open Web Text)
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.3083. Min Range: -5.3083
Max Act: 5.1833. Min Act: -0.1700
Data Index: 6187952 (Open Web Text)
Max Activating Token Index: 155
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.3083. Min Range: -5.3083
Max Act: 5.1833. Min Act: -0.1700
Data Index: 2736637 (Open Web Text)
Max Activating Token Index: 28
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.3083. Min Range: -5.3083
Max Act: 5.1208. Min Act: -0.1700
Data Index: 5782188 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.3083. Min Range: -5.3083
Max Act: 5.1208. Min Act: -0.1700
Data Index: 6058973 (Open Web Text)
Max Activating Token Index: 116
Click toggle to see full text
Truncated
Full Text #19