Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3049 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 1.8152. Min Range: -1.8152
Max Act: 1.8152. Min Act: -0.1699
Data Index: 6989074 (Open Web Text)
Max Activating Token Index: 175
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.8152. Min Range: -1.8152
Max Act: 1.7550. Min Act: -0.1692
Data Index: 6456359 (Open Web Text)
Max Activating Token Index: 197
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.8152. Min Range: -1.8152
Max Act: 1.7722. Min Act: -0.1700
Data Index: 8466807 (Open Web Text)
Max Activating Token Index: 218
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.8152. Min Range: -1.8152
Max Act: 1.7636. Min Act: -0.1700
Data Index: 7086832 (Open Web Text)
Max Activating Token Index: 168
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.8152. Min Range: -1.8152
Max Act: 1.7463. Min Act: -0.1699
Data Index: 2461644 (Open Web Text)
Max Activating Token Index: 207
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.8152. Min Range: -1.8152
Max Act: 1.7463. Min Act: -0.1694
Data Index: 4789197 (Open Web Text)
Max Activating Token Index: 191
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.8152. Min Range: -1.8152
Max Act: 1.7290. Min Act: -0.1700
Data Index: 1777945 (Open Web Text)
Max Activating Token Index: 154
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.8152. Min Range: -1.8152
Max Act: 1.7290. Min Act: -0.1699
Data Index: 6908572 (Open Web Text)
Max Activating Token Index: 579
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.8152. Min Range: -1.8152
Max Act: 1.7290. Min Act: -0.1698
Data Index: 6381262 (Open Web Text)
Max Activating Token Index: 63
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.8152. Min Range: -1.8152
Max Act: 1.7290. Min Act: -0.1699
Data Index: 3229045 (Open Web Text)
Max Activating Token Index: 46
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.8152. Min Range: -1.8152
Max Act: 1.7377. Min Act: -0.1700
Data Index: 7647102 (Open Web Text)
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.8152. Min Range: -1.8152
Max Act: 1.7290. Min Act: -0.1700
Data Index: 7259187 (Open Web Text)
Max Activating Token Index: 220
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.8152. Min Range: -1.8152
Max Act: 1.7290. Min Act: -0.1700
Data Index: 1421028 (Open Web Text)
Max Activating Token Index: 197
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.8152. Min Range: -1.8152
Max Act: 1.7204. Min Act: -0.1700
Data Index: 1998018 (Open Web Text)
Max Activating Token Index: 179
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.8152. Min Range: -1.8152
Max Act: 1.7117. Min Act: -0.1700
Data Index: 5333933 (Open Web Text)
Max Activating Token Index: 146
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.8152. Min Range: -1.8152
Max Act: 1.7117. Min Act: -0.1700
Data Index: 8621372 (Open Web Text)
Max Activating Token Index: 141
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.8152. Min Range: -1.8152
Max Act: 1.7117. Min Act: -0.1700
Data Index: 2665854 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.8152. Min Range: -1.8152
Max Act: 1.7117. Min Act: -0.1699
Data Index: 2563695 (Open Web Text)
Max Activating Token Index: 198
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.8152. Min Range: -1.8152
Max Act: 1.7117. Min Act: -0.1699
Data Index: 3628991 (Open Web Text)
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.8152. Min Range: -1.8152
Max Act: 1.7117. Min Act: -0.1700
Data Index: 6381261 (Open Web Text)
Max Activating Token Index: 234
Click toggle to see full text
Truncated
Full Text #19