Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3216 in Layer 16
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.7198. Min Range: -4.7198
Max Act: 4.7198. Min Act: -0.1700
Data Index: 4822359 (Open Web Text)
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.7198. Min Range: -4.7198
Max Act: 4.2822. Min Act: -0.1700
Data Index: 4822360 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.7198. Min Range: -4.7198
Max Act: 4.2822. Min Act: -0.1700
Data Index: 898255 (Open Web Text)
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.7198. Min Range: -4.7198
Max Act: 4.2510. Min Act: -0.1700
Data Index: 5634847 (Open Web Text)
Max Activating Token Index: 826
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.7198. Min Range: -4.7198
Max Act: 4.2197. Min Act: -0.1700
Data Index: 1121573 (Open Web Text)
Max Activating Token Index: 256
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.7198. Min Range: -4.7198
Max Act: 4.2510. Min Act: -0.1700
Data Index: 4544874 (Open Web Text)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.7198. Min Range: -4.7198
Max Act: 4.2197. Min Act: -0.1700
Data Index: 1493943 (Open Web Text)
Max Activating Token Index: 660
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.7198. Min Range: -4.7198
Max Act: 4.2197. Min Act: -0.1700
Data Index: 2206877 (Open Web Text)
Max Activating Token Index: 402
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.7198. Min Range: -4.7198
Max Act: 4.1885. Min Act: -0.1700
Data Index: 8016645 (Open Web Text)
Max Activating Token Index: 323
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.7198. Min Range: -4.7198
Max Act: 4.1885. Min Act: -0.1700
Data Index: 2315072 (Open Web Text)
Max Activating Token Index: 712
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.7198. Min Range: -4.7198
Max Act: 4.1885. Min Act: -0.1700
Data Index: 8735052 (Open Web Text)
Max Activating Token Index: 250
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.7198. Min Range: -4.7198
Max Act: 4.1885. Min Act: -0.1700
Data Index: 7640100 (Open Web Text)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.7198. Min Range: -4.7198
Max Act: 4.1572. Min Act: -0.1700
Data Index: 3572293 (Open Web Text)
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.7198. Min Range: -4.7198
Max Act: 4.1260. Min Act: -0.1700
Data Index: 543908 (Open Web Text)
Max Activating Token Index: 615
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.7198. Min Range: -4.7198
Max Act: 4.1260. Min Act: -0.1700
Data Index: 5700058 (Open Web Text)
Max Activating Token Index: 269
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.7198. Min Range: -4.7198
Max Act: 4.1572. Min Act: -0.1700
Data Index: 203905 (Open Web Text)
Max Activating Token Index: 603
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.7198. Min Range: -4.7198
Max Act: 4.1260. Min Act: -0.1700
Data Index: 4544879 (Open Web Text)
Max Activating Token Index: 459
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.7198. Min Range: -4.7198
Max Act: 4.1260. Min Act: -0.1700
Data Index: 7467155 (Open Web Text)
Max Activating Token Index: 640
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.7198. Min Range: -4.7198
Max Act: 4.0947. Min Act: -0.1700
Data Index: 4587126 (Open Web Text)
Max Activating Token Index: 494
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.7198. Min Range: -4.7198
Max Act: 4.0947. Min Act: -0.1700
Data Index: 4652768 (Open Web Text)
Max Activating Token Index: 114
Click toggle to see full text
Truncated
Full Text #19