Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3184 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.9981. Min Range: -5.9981
Max Act: 5.9981. Min Act: -0.1700
Data Index: 6554285 (Open Web Text)
Max Activating Token Index: 999
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9981. Min Range: -5.9981
Max Act: 5.9356. Min Act: -0.1700
Data Index: 5374006 (Open Web Text)
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9981. Min Range: -5.9981
Max Act: 5.9356. Min Act: -0.1700
Data Index: 2798669 (Open Web Text)
Max Activating Token Index: 408
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9981. Min Range: -5.9981
Max Act: 5.8731. Min Act: -0.1700
Data Index: 8439700 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9981. Min Range: -5.9981
Max Act: 5.8731. Min Act: -0.1700
Data Index: 7554481 (Open Web Text)
Max Activating Token Index: 1016
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9981. Min Range: -5.9981
Max Act: 5.8418. Min Act: -0.1700
Data Index: 5741001 (Open Web Text)
Max Activating Token Index: 682
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9981. Min Range: -5.9981
Max Act: 5.8106. Min Act: -0.1700
Data Index: 1917169 (Open Web Text)
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9981. Min Range: -5.9981
Max Act: 5.7481. Min Act: -0.1700
Data Index: 3415244 (Open Web Text)
Max Activating Token Index: 529
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9981. Min Range: -5.9981
Max Act: 5.7481. Min Act: -0.1700
Data Index: 5181750 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9981. Min Range: -5.9981
Max Act: 5.7168. Min Act: -0.1700
Data Index: 4162957 (Open Web Text)
Max Activating Token Index: 862
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9981. Min Range: -5.9981
Max Act: 5.7168. Min Act: -0.1700
Data Index: 7558002 (Open Web Text)
Max Activating Token Index: 730
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9981. Min Range: -5.9981
Max Act: 5.7168. Min Act: -0.1700
Data Index: 1854845 (Open Web Text)
Max Activating Token Index: 695
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9981. Min Range: -5.9981
Max Act: 5.6543. Min Act: -0.1700
Data Index: 5849470 (Open Web Text)
Max Activating Token Index: 378
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9981. Min Range: -5.9981
Max Act: 5.6543. Min Act: -0.1700
Data Index: 5177969 (Open Web Text)
Max Activating Token Index: 296
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9981. Min Range: -5.9981
Max Act: 5.6543. Min Act: -0.1700
Data Index: 4560916 (Open Web Text)
Max Activating Token Index: 383
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9981. Min Range: -5.9981
Max Act: 5.6543. Min Act: -0.1700
Data Index: 554759 (Open Web Text)
Max Activating Token Index: 368
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9981. Min Range: -5.9981
Max Act: 5.6231. Min Act: -0.1700
Data Index: 2894766 (Open Web Text)
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9981. Min Range: -5.9981
Max Act: 5.6231. Min Act: -0.1700
Data Index: 3691681 (Open Web Text)
Max Activating Token Index: 664
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9981. Min Range: -5.9981
Max Act: 5.6231. Min Act: -0.1700
Data Index: 2131727 (Open Web Text)
Max Activating Token Index: 422
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9981. Min Range: -5.9981
Max Act: 5.6231. Min Act: -0.1700
Data Index: 4641655 (Open Web Text)
Max Activating Token Index: 175
Click toggle to see full text
Truncated
Full Text #19