Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 28 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.7772. Min Range: -4.7772
Max Act: 4.7772. Min Act: -0.1700
Data Index: 8646565 (Open Web Text)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.7772. Min Range: -4.7772
Max Act: 4.7459. Min Act: -0.1700
Data Index: 4985800 (Open Web Text)
Max Activating Token Index: 181
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.7772. Min Range: -4.7772
Max Act: 4.7147. Min Act: -0.1700
Data Index: 926795 (Open Web Text)
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.7772. Min Range: -4.7772
Max Act: 4.7147. Min Act: -0.1700
Data Index: 4828292 (Open Web Text)
Max Activating Token Index: 193
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.7772. Min Range: -4.7772
Max Act: 4.6834. Min Act: -0.1700
Data Index: 5828590 (Open Web Text)
Max Activating Token Index: 163
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.7772. Min Range: -4.7772
Max Act: 4.6834. Min Act: -0.1700
Data Index: 5629554 (Open Web Text)
Max Activating Token Index: 169
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.7772. Min Range: -4.7772
Max Act: 4.6834. Min Act: -0.1700
Data Index: 3622760 (Open Web Text)
Max Activating Token Index: 63
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.7772. Min Range: -4.7772
Max Act: 4.6522. Min Act: -0.1700
Data Index: 5342032 (Open Web Text)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.7772. Min Range: -4.7772
Max Act: 4.6522. Min Act: -0.1700
Data Index: 5323381 (Open Web Text)
Max Activating Token Index: 249
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.7772. Min Range: -4.7772
Max Act: 4.6522. Min Act: -0.1700
Data Index: 181602 (Open Web Text)
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.7772. Min Range: -4.7772
Max Act: 4.6209. Min Act: -0.1700
Data Index: 5216113 (Open Web Text)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.7772. Min Range: -4.7772
Max Act: 4.6209. Min Act: -0.1700
Data Index: 1415382 (Open Web Text)
Max Activating Token Index: 156
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.7772. Min Range: -4.7772
Max Act: 4.6522. Min Act: -0.1700
Data Index: 7980971 (Open Web Text)
Max Activating Token Index: 197
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.7772. Min Range: -4.7772
Max Act: 4.6522. Min Act: -0.1700
Data Index: 3588339 (Open Web Text)
Max Activating Token Index: 53
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.7772. Min Range: -4.7772
Max Act: 4.6522. Min Act: -0.1700
Data Index: 7884260 (Open Web Text)
Max Activating Token Index: 213
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.7772. Min Range: -4.7772
Max Act: 4.6209. Min Act: -0.1700
Data Index: 2892853 (Open Web Text)
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.7772. Min Range: -4.7772
Max Act: 4.6209. Min Act: -0.1700
Data Index: 3998476 (Open Web Text)
Max Activating Token Index: 374
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.7772. Min Range: -4.7772
Max Act: 4.6209. Min Act: -0.1700
Data Index: 1872673 (Open Web Text)
Max Activating Token Index: 64
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.7772. Min Range: -4.7772
Max Act: 4.6209. Min Act: -0.1700
Data Index: 4978257 (Open Web Text)
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.7772. Min Range: -4.7772
Max Act: 4.6209. Min Act: -0.1700
Data Index: 5562255 (Open Web Text)
Max Activating Token Index: 204
Click toggle to see full text
Truncated
Full Text #19