Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3295 in Layer 27
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.8361. Min Range: -7.8361
Max Act: 7.8361. Min Act: -0.1700
Data Index: 6736630 (Open Web Text)
Max Activating Token Index: 55
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.8361. Min Range: -7.8361
Max Act: 7.6486. Min Act: -0.1700
Data Index: 8222614 (Open Web Text)
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.8361. Min Range: -7.8361
Max Act: 7.5236. Min Act: -0.1700
Data Index: 4182536 (Open Web Text)
Max Activating Token Index: 779
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.8361. Min Range: -7.8361
Max Act: 7.5236. Min Act: -0.1700
Data Index: 7329784 (Open Web Text)
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.8361. Min Range: -7.8361
Max Act: 7.5236. Min Act: -0.1700
Data Index: 2708753 (Open Web Text)
Max Activating Token Index: 698
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.8361. Min Range: -7.8361
Max Act: 7.5861. Min Act: -0.1700
Data Index: 5727849 (Open Web Text)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.8361. Min Range: -7.8361
Max Act: 7.5236. Min Act: -0.1700
Data Index: 2329255 (Open Web Text)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.8361. Min Range: -7.8361
Max Act: 7.4611. Min Act: -0.1700
Data Index: 6053296 (Open Web Text)
Max Activating Token Index: 81
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.8361. Min Range: -7.8361
Max Act: 7.4611. Min Act: -0.1700
Data Index: 4566992 (Open Web Text)
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.8361. Min Range: -7.8361
Max Act: 7.4299. Min Act: -0.1700
Data Index: 7926386 (Open Web Text)
Max Activating Token Index: 479
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.8361. Min Range: -7.8361
Max Act: 7.3986. Min Act: -0.1700
Data Index: 367595 (Open Web Text)
Max Activating Token Index: 933
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.8361. Min Range: -7.8361
Max Act: 7.3986. Min Act: -0.1700
Data Index: 6763431 (Open Web Text)
Max Activating Token Index: 377
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.8361. Min Range: -7.8361
Max Act: 7.3361. Min Act: -0.1700
Data Index: 1200588 (Open Web Text)
Max Activating Token Index: 40
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.8361. Min Range: -7.8361
Max Act: 7.3361. Min Act: -0.1700
Data Index: 4666159 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.8361. Min Range: -7.8361
Max Act: 7.2736. Min Act: -0.1700
Data Index: 2266023 (Open Web Text)
Max Activating Token Index: 672
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.8361. Min Range: -7.8361
Max Act: 7.2424. Min Act: -0.1700
Data Index: 1833442 (Open Web Text)
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.8361. Min Range: -7.8361
Max Act: 7.2111. Min Act: -0.1700
Data Index: 2112789 (Open Web Text)
Max Activating Token Index: 622
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.8361. Min Range: -7.8361
Max Act: 7.1799. Min Act: -0.1700
Data Index: 6560835 (Open Web Text)
Max Activating Token Index: 219
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.8361. Min Range: -7.8361
Max Act: 7.1799. Min Act: -0.1700
Data Index: 7571172 (Open Web Text)
Max Activating Token Index: 834
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.8361. Min Range: -7.8361
Max Act: 7.2111. Min Act: -0.1700
Data Index: 377794 (Open Web Text)
Max Activating Token Index: 178
Click toggle to see full text
Truncated
Full Text #19