Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3920 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.5224. Min Range: -7.5224
Max Act: 7.5224. Min Act: -0.1700
Data Index: 1532358 (Open Web Text)
Max Activating Token Index: 618
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.5224. Min Range: -7.5224
Max Act: 7.4911. Min Act: -0.1700
Data Index: 8499027 (Open Web Text)
Max Activating Token Index: 317
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.5224. Min Range: -7.5224
Max Act: 7.3661. Min Act: -0.1700
Data Index: 7828905 (Open Web Text)
Max Activating Token Index: 682
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.5224. Min Range: -7.5224
Max Act: 7.3661. Min Act: -0.1700
Data Index: 5692672 (Open Web Text)
Max Activating Token Index: 848
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.5224. Min Range: -7.5224
Max Act: 7.3349. Min Act: -0.1700
Data Index: 3557427 (Open Web Text)
Max Activating Token Index: 922
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.5224. Min Range: -7.5224
Max Act: 7.3349. Min Act: -0.1700
Data Index: 5236204 (Open Web Text)
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.5224. Min Range: -7.5224
Max Act: 7.3349. Min Act: -0.1700
Data Index: 3205323 (Open Web Text)
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.5224. Min Range: -7.5224
Max Act: 7.3036. Min Act: -0.1700
Data Index: 3697169 (Open Web Text)
Max Activating Token Index: 111
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.5224. Min Range: -7.5224
Max Act: 7.3036. Min Act: -0.1700
Data Index: 2888229 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.5224. Min Range: -7.5224
Max Act: 7.2724. Min Act: -0.1700
Data Index: 6572331 (Open Web Text)
Max Activating Token Index: 546
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.5224. Min Range: -7.5224
Max Act: 7.2724. Min Act: -0.1700
Data Index: 2189194 (Open Web Text)
Max Activating Token Index: 725
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.5224. Min Range: -7.5224
Max Act: 7.2724. Min Act: -0.1700
Data Index: 584516 (Open Web Text)
Max Activating Token Index: 226
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.5224. Min Range: -7.5224
Max Act: 7.1786. Min Act: -0.1700
Data Index: 3319148 (Open Web Text)
Max Activating Token Index: 246
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.5224. Min Range: -7.5224
Max Act: 7.2099. Min Act: -0.1700
Data Index: 5827915 (Open Web Text)
Max Activating Token Index: 43
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.5224. Min Range: -7.5224
Max Act: 7.2099. Min Act: -0.1700
Data Index: 7760629 (Open Web Text)
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.5224. Min Range: -7.5224
Max Act: 7.1786. Min Act: -0.1700
Data Index: 2827831 (Open Web Text)
Max Activating Token Index: 905
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.5224. Min Range: -7.5224
Max Act: 7.1786. Min Act: -0.1700
Data Index: 6212359 (Open Web Text)
Max Activating Token Index: 97
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.5224. Min Range: -7.5224
Max Act: 7.1786. Min Act: -0.1700
Data Index: 840000 (Open Web Text)
Max Activating Token Index: 515
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.5224. Min Range: -7.5224
Max Act: 7.1786. Min Act: -0.1700
Data Index: 2413015 (Open Web Text)
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.5224. Min Range: -7.5224
Max Act: 7.1474. Min Act: -0.1700
Data Index: 5326908 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #19