Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3359 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 11.8489. Min Range: -11.8489
Max Act: 11.8489. Min Act: -0.1700
Data Index: 7201463 (Open Web Text)
Max Activating Token Index: 483
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 11.8489. Min Range: -11.8489
Max Act: 11.7239. Min Act: -0.1700
Data Index: 2069833 (Open Web Text)
Max Activating Token Index: 378
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 11.8489. Min Range: -11.8489
Max Act: 11.6614. Min Act: -0.1700
Data Index: 4407565 (Open Web Text)
Max Activating Token Index: 918
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 11.8489. Min Range: -11.8489
Max Act: 11.6614. Min Act: -0.1700
Data Index: 7447442 (Open Web Text)
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 11.8489. Min Range: -11.8489
Max Act: 11.6614. Min Act: -0.1700
Data Index: 4078491 (Open Web Text)
Max Activating Token Index: 887
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 11.8489. Min Range: -11.8489
Max Act: 11.5989. Min Act: -0.1700
Data Index: 1452181 (Open Web Text)
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 11.8489. Min Range: -11.8489
Max Act: 11.5989. Min Act: -0.1700
Data Index: 7645883 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 11.8489. Min Range: -11.8489
Max Act: 11.5989. Min Act: -0.1700
Data Index: 478434 (Open Web Text)
Max Activating Token Index: 511
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 11.8489. Min Range: -11.8489
Max Act: 11.5364. Min Act: -0.1700
Data Index: 6577167 (Open Web Text)
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 11.8489. Min Range: -11.8489
Max Act: 11.4739. Min Act: -0.1700
Data Index: 660906 (Open Web Text)
Max Activating Token Index: 897
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 11.8489. Min Range: -11.8489
Max Act: 11.4114. Min Act: -0.1700
Data Index: 6387964 (Open Web Text)
Max Activating Token Index: 479
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 11.8489. Min Range: -11.8489
Max Act: 11.4114. Min Act: -0.1700
Data Index: 1431116 (Open Web Text)
Max Activating Token Index: 421
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 11.8489. Min Range: -11.8489
Max Act: 11.3489. Min Act: -0.1700
Data Index: 4343053 (Open Web Text)
Max Activating Token Index: 759
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 11.8489. Min Range: -11.8489
Max Act: 11.4114. Min Act: -0.1700
Data Index: 6627832 (Open Web Text)
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 11.8489. Min Range: -11.8489
Max Act: 11.4114. Min Act: -0.1700
Data Index: 1987328 (Open Web Text)
Max Activating Token Index: 982
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 11.8489. Min Range: -11.8489
Max Act: 11.3489. Min Act: -0.1700
Data Index: 7176263 (Open Web Text)
Max Activating Token Index: 814
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 11.8489. Min Range: -11.8489
Max Act: 11.3489. Min Act: -0.1700
Data Index: 3855316 (Open Web Text)
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 11.8489. Min Range: -11.8489
Max Act: 11.3489. Min Act: -0.1700
Data Index: 795041 (Open Web Text)
Max Activating Token Index: 984
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 11.8489. Min Range: -11.8489
Max Act: 11.3489. Min Act: -0.1700
Data Index: 4381589 (Open Web Text)
Max Activating Token Index: 731
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 11.8489. Min Range: -11.8489
Max Act: 11.3489. Min Act: -0.1700
Data Index: 1863865 (Open Web Text)
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #19