Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 170 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.6770. Min Range: -4.6770
Max Act: 4.6770. Min Act: -0.1700
Data Index: 3635799 (Open Web Text)
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.6770. Min Range: -4.6770
Max Act: 4.6770. Min Act: -0.1700
Data Index: 805372 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.6770. Min Range: -4.6770
Max Act: 4.6770. Min Act: -0.1700
Data Index: 2770439 (Open Web Text)
Max Activating Token Index: 187
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.6770. Min Range: -4.6770
Max Act: 4.6145. Min Act: -0.1700
Data Index: 6025985 (Open Web Text)
Max Activating Token Index: 85
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.6770. Min Range: -4.6770
Max Act: 4.6457. Min Act: -0.1700
Data Index: 1375342 (Open Web Text)
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.6770. Min Range: -4.6770
Max Act: 4.6457. Min Act: -0.1700
Data Index: 3836252 (Open Web Text)
Max Activating Token Index: 51
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.6770. Min Range: -4.6770
Max Act: 4.6457. Min Act: -0.1700
Data Index: 291440 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.6770. Min Range: -4.6770
Max Act: 4.6145. Min Act: -0.1700
Data Index: 6565702 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.6770. Min Range: -4.6770
Max Act: 4.6145. Min Act: -0.1700
Data Index: 8788004 (Open Web Text)
Max Activating Token Index: 143
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.6770. Min Range: -4.6770
Max Act: 4.6145. Min Act: -0.1700
Data Index: 3619315 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.6770. Min Range: -4.6770
Max Act: 4.6145. Min Act: -0.1700
Data Index: 1751158 (Open Web Text)
Max Activating Token Index: 92
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.6770. Min Range: -4.6770
Max Act: 4.6145. Min Act: -0.1700
Data Index: 8415173 (Open Web Text)
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.6770. Min Range: -4.6770
Max Act: 4.6145. Min Act: -0.1700
Data Index: 6447397 (Open Web Text)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.6770. Min Range: -4.6770
Max Act: 4.6145. Min Act: -0.1700
Data Index: 1321048 (Open Web Text)
Max Activating Token Index: 168
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.6770. Min Range: -4.6770
Max Act: 4.6145. Min Act: -0.1700
Data Index: 2097947 (Open Web Text)
Max Activating Token Index: 52
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.6770. Min Range: -4.6770
Max Act: 4.6457. Min Act: -0.1700
Data Index: 6397775 (Open Web Text)
Max Activating Token Index: 176
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.6770. Min Range: -4.6770
Max Act: 4.6145. Min Act: -0.1700
Data Index: 131433 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.6770. Min Range: -4.6770
Max Act: 4.5520. Min Act: -0.1700
Data Index: 750465 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.6770. Min Range: -4.6770
Max Act: 4.5832. Min Act: -0.1700
Data Index: 976949 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.6770. Min Range: -4.6770
Max Act: 4.5832. Min Act: -0.1700
Data Index: 5088248 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #19