Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 755 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.8628. Min Range: -3.8628
Max Act: 3.8628. Min Act: -0.1700
Data Index: 6296118 (Open Web Text)
Max Activating Token Index: 396
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.8628. Min Range: -3.8628
Max Act: 3.8002. Min Act: -0.1700
Data Index: 1373339 (Open Web Text)
Max Activating Token Index: 113
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.8628. Min Range: -3.8628
Max Act: 3.7690. Min Act: -0.1700
Data Index: 4634251 (Open Web Text)
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.8628. Min Range: -3.8628
Max Act: 3.7377. Min Act: -0.1700
Data Index: 2546891 (Open Web Text)
Max Activating Token Index: 912
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.8628. Min Range: -3.8628
Max Act: 3.7377. Min Act: -0.1700
Data Index: 802357 (Open Web Text)
Max Activating Token Index: 657
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.8628. Min Range: -3.8628
Max Act: 3.7064. Min Act: -0.1700
Data Index: 5717979 (Open Web Text)
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.8628. Min Range: -3.8628
Max Act: 3.6751. Min Act: -0.1700
Data Index: 3452976 (Open Web Text)
Max Activating Token Index: 181
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.8628. Min Range: -3.8628
Max Act: 3.7064. Min Act: -0.1700
Data Index: 5455892 (Open Web Text)
Max Activating Token Index: 211
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.8628. Min Range: -3.8628
Max Act: 3.6751. Min Act: -0.1700
Data Index: 5302290 (Open Web Text)
Max Activating Token Index: 218
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.8628. Min Range: -3.8628
Max Act: 3.6438. Min Act: -0.1700
Data Index: 4283137 (Open Web Text)
Max Activating Token Index: 252
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.8628. Min Range: -3.8628
Max Act: 3.6438. Min Act: -0.1700
Data Index: 4528800 (Open Web Text)
Max Activating Token Index: 699
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.8628. Min Range: -3.8628
Max Act: 3.6751. Min Act: -0.1700
Data Index: 1669278 (Open Web Text)
Max Activating Token Index: 439
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.8628. Min Range: -3.8628
Max Act: 3.6751. Min Act: -0.1700
Data Index: 1373340 (Open Web Text)
Max Activating Token Index: 199
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.8628. Min Range: -3.8628
Max Act: 3.6438. Min Act: -0.1700
Data Index: 5240137 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.8628. Min Range: -3.8628
Max Act: 3.6438. Min Act: -0.1700
Data Index: 1422691 (Open Web Text)
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.8628. Min Range: -3.8628
Max Act: 3.6438. Min Act: -0.1700
Data Index: 983185 (Open Web Text)
Max Activating Token Index: 786
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.8628. Min Range: -3.8628
Max Act: 3.6438. Min Act: -0.1700
Data Index: 871550 (Open Web Text)
Max Activating Token Index: 295
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.8628. Min Range: -3.8628
Max Act: 3.6438. Min Act: -0.1700
Data Index: 6536106 (Open Web Text)
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.8628. Min Range: -3.8628
Max Act: 3.6438. Min Act: -0.1700
Data Index: 1205493 (Open Web Text)
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.8628. Min Range: -3.8628
Max Act: 3.6438. Min Act: -0.1700
Data Index: 5040444 (Open Web Text)
Max Activating Token Index: 960
Click toggle to see full text
Truncated
Full Text #19