Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3750 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.4053. Min Range: -6.4053
Max Act: 6.4053. Min Act: -0.1700
Data Index: 4342536 (Open Web Text)
Max Activating Token Index: 732
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.4053. Min Range: -6.4053
Max Act: 6.2178. Min Act: -0.1700
Data Index: 2758041 (Open Web Text)
Max Activating Token Index: 721
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.4053. Min Range: -6.4053
Max Act: 5.9990. Min Act: -0.1700
Data Index: 3181981 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.4053. Min Range: -6.4053
Max Act: 5.9678. Min Act: -0.1700
Data Index: 610495 (Open Web Text)
Max Activating Token Index: 311
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.4053. Min Range: -6.4053
Max Act: 5.9053. Min Act: -0.1700
Data Index: 3354202 (Open Web Text)
Max Activating Token Index: 318
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.4053. Min Range: -6.4053
Max Act: 5.8740. Min Act: -0.1700
Data Index: 4020316 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.4053. Min Range: -6.4053
Max Act: 5.8428. Min Act: -0.1700
Data Index: 256960 (Open Web Text)
Max Activating Token Index: 245
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.4053. Min Range: -6.4053
Max Act: 5.8428. Min Act: -0.1700
Data Index: 1985780 (Open Web Text)
Max Activating Token Index: 167
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.4053. Min Range: -6.4053
Max Act: 5.8428. Min Act: -0.1700
Data Index: 8317070 (Open Web Text)
Max Activating Token Index: 891
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.4053. Min Range: -6.4053
Max Act: 5.8115. Min Act: -0.1700
Data Index: 1160581 (Open Web Text)
Max Activating Token Index: 199
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.4053. Min Range: -6.4053
Max Act: 5.7803. Min Act: -0.1700
Data Index: 6794608 (Open Web Text)
Max Activating Token Index: 33
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.4053. Min Range: -6.4053
Max Act: 5.7490. Min Act: -0.1700
Data Index: 2723918 (Open Web Text)
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.4053. Min Range: -6.4053
Max Act: 5.6865. Min Act: -0.1700
Data Index: 4302755 (Open Web Text)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.4053. Min Range: -6.4053
Max Act: 5.6865. Min Act: -0.1700
Data Index: 5764766 (Open Web Text)
Max Activating Token Index: 785
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.4053. Min Range: -6.4053
Max Act: 5.6553. Min Act: -0.1700
Data Index: 6109185 (Open Web Text)
Max Activating Token Index: 86
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.4053. Min Range: -6.4053
Max Act: 5.6553. Min Act: -0.1700
Data Index: 5624014 (Open Web Text)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.4053. Min Range: -6.4053
Max Act: 5.6240. Min Act: -0.1700
Data Index: 1913981 (Open Web Text)
Max Activating Token Index: 165
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.4053. Min Range: -6.4053
Max Act: 5.6240. Min Act: -0.1700
Data Index: 87103 (Open Web Text)
Max Activating Token Index: 73
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.4053. Min Range: -6.4053
Max Act: 5.6553. Min Act: -0.1700
Data Index: 4282663 (Open Web Text)
Max Activating Token Index: 482
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.4053. Min Range: -6.4053
Max Act: 5.6240. Min Act: -0.1700
Data Index: 3308637 (Open Web Text)
Max Activating Token Index: 1011
Click toggle to see full text
Truncated
Full Text #19