Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2983 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.1013. Min Range: -6.1013
Max Act: 6.1013. Min Act: -0.1700
Data Index: 6493128 (Open Web Text)
Max Activating Token Index: 748
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.1013. Min Range: -6.1013
Max Act: 5.7888. Min Act: -0.1700
Data Index: 8350506 (Open Web Text)
Max Activating Token Index: 71
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.1013. Min Range: -6.1013
Max Act: 5.7263. Min Act: -0.1700
Data Index: 339185 (Open Web Text)
Max Activating Token Index: 910
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.1013. Min Range: -6.1013
Max Act: 5.7263. Min Act: -0.1700
Data Index: 1647198 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.1013. Min Range: -6.1013
Max Act: 5.6326. Min Act: -0.1700
Data Index: 853231 (Open Web Text)
Max Activating Token Index: 913
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.1013. Min Range: -6.1013
Max Act: 5.6326. Min Act: -0.1700
Data Index: 5866961 (Open Web Text)
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.1013. Min Range: -6.1013
Max Act: 5.6326. Min Act: -0.1700
Data Index: 2695974 (Open Web Text)
Max Activating Token Index: 253
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.1013. Min Range: -6.1013
Max Act: 5.6326. Min Act: -0.1700
Data Index: 3164535 (Open Web Text)
Max Activating Token Index: 794
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.1013. Min Range: -6.1013
Max Act: 5.6013. Min Act: -0.1700
Data Index: 6863867 (Open Web Text)
Max Activating Token Index: 951
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.1013. Min Range: -6.1013
Max Act: 5.5701. Min Act: -0.1700
Data Index: 4220265 (Open Web Text)
Max Activating Token Index: 334
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.1013. Min Range: -6.1013
Max Act: 5.5076. Min Act: -0.1700
Data Index: 1176318 (Open Web Text)
Max Activating Token Index: 653
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.1013. Min Range: -6.1013
Max Act: 5.5388. Min Act: -0.1700
Data Index: 4664205 (Open Web Text)
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.1013. Min Range: -6.1013
Max Act: 5.5076. Min Act: -0.1700
Data Index: 6781942 (Open Web Text)
Max Activating Token Index: 868
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.1013. Min Range: -6.1013
Max Act: 5.4451. Min Act: -0.1700
Data Index: 5887154 (Open Web Text)
Max Activating Token Index: 308
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.1013. Min Range: -6.1013
Max Act: 5.4451. Min Act: -0.1700
Data Index: 7182407 (Open Web Text)
Max Activating Token Index: 122
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.1013. Min Range: -6.1013
Max Act: 5.4451. Min Act: -0.1700
Data Index: 2876659 (Open Web Text)
Max Activating Token Index: 127
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.1013. Min Range: -6.1013
Max Act: 5.4451. Min Act: -0.1700
Data Index: 6863870 (Open Web Text)
Max Activating Token Index: 895
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.1013. Min Range: -6.1013
Max Act: 5.3826. Min Act: -0.1700
Data Index: 2923519 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.1013. Min Range: -6.1013
Max Act: 5.3513. Min Act: -0.1700
Data Index: 1460046 (Open Web Text)
Max Activating Token Index: 496
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.1013. Min Range: -6.1013
Max Act: 5.3826. Min Act: -0.1700
Data Index: 721650 (Open Web Text)
Max Activating Token Index: 216
Click toggle to see full text
Truncated
Full Text #19