Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5659 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.5993. Min Range: -6.5993
Max Act: 6.5993. Min Act: -0.1700
Data Index: 4601772 (Open Web Text)
Max Activating Token Index: 752
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.5993. Min Range: -6.5993
Max Act: 6.4743. Min Act: -0.1700
Data Index: 4103148 (Open Web Text)
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.5993. Min Range: -6.5993
Max Act: 6.4743. Min Act: -0.1700
Data Index: 481533 (Open Web Text)
Max Activating Token Index: 952
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.5993. Min Range: -6.5993
Max Act: 6.4430. Min Act: -0.1700
Data Index: 6383718 (Open Web Text)
Max Activating Token Index: 664
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.5993. Min Range: -6.5993
Max Act: 6.3493. Min Act: -0.1700
Data Index: 8433080 (Open Web Text)
Max Activating Token Index: 875
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.5993. Min Range: -6.5993
Max Act: 6.3180. Min Act: -0.1700
Data Index: 782282 (Open Web Text)
Max Activating Token Index: 590
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.5993. Min Range: -6.5993
Max Act: 6.3180. Min Act: -0.1700
Data Index: 7143934 (Open Web Text)
Max Activating Token Index: 956
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.5993. Min Range: -6.5993
Max Act: 6.2868. Min Act: -0.1700
Data Index: 3804451 (Open Web Text)
Max Activating Token Index: 305
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.5993. Min Range: -6.5993
Max Act: 6.2868. Min Act: -0.1700
Data Index: 3802105 (Open Web Text)
Max Activating Token Index: 981
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.5993. Min Range: -6.5993
Max Act: 6.2243. Min Act: -0.1700
Data Index: 1386591 (Open Web Text)
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.5993. Min Range: -6.5993
Max Act: 6.1618. Min Act: -0.1700
Data Index: 442830 (Open Web Text)
Max Activating Token Index: 826
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.5993. Min Range: -6.5993
Max Act: 6.1305. Min Act: -0.1700
Data Index: 5434331 (Open Web Text)
Max Activating Token Index: 820
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.5993. Min Range: -6.5993
Max Act: 6.1305. Min Act: -0.1700
Data Index: 2610231 (Open Web Text)
Max Activating Token Index: 114
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.5993. Min Range: -6.5993
Max Act: 6.1305. Min Act: -0.1700
Data Index: 4449011 (Open Web Text)
Max Activating Token Index: 579
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.5993. Min Range: -6.5993
Max Act: 6.0680. Min Act: -0.1700
Data Index: 2844672 (Open Web Text)
Max Activating Token Index: 974
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.5993. Min Range: -6.5993
Max Act: 6.0993. Min Act: -0.1700
Data Index: 5690846 (Open Web Text)
Max Activating Token Index: 938
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.5993. Min Range: -6.5993
Max Act: 6.0993. Min Act: -0.1700
Data Index: 5598457 (Open Web Text)
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.5993. Min Range: -6.5993
Max Act: 6.0680. Min Act: -0.1700
Data Index: 73700 (Open Web Text)
Max Activating Token Index: 665
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.5993. Min Range: -6.5993
Max Act: 6.0680. Min Act: -0.1700
Data Index: 4215989 (Open Web Text)
Max Activating Token Index: 925
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.5993. Min Range: -6.5993
Max Act: 6.0680. Min Act: -0.1700
Data Index: 2453554 (Open Web Text)
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #19