Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4884 in Layer 6
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.8409. Min Range: -5.8409
Max Act: 5.8409. Min Act: -0.1700
Data Index: 2382346 (Open Web Text)
Max Activating Token Index: 51
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.8409. Min Range: -5.8409
Max Act: 5.6846. Min Act: -0.1700
Data Index: 5560510 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.8409. Min Range: -5.8409
Max Act: 5.6846. Min Act: -0.1700
Data Index: 295318 (Open Web Text)
Max Activating Token Index: 48
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.8409. Min Range: -5.8409
Max Act: 5.6534. Min Act: -0.1700
Data Index: 295320 (Open Web Text)
Max Activating Token Index: 390
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.8409. Min Range: -5.8409
Max Act: 5.6221. Min Act: -0.1700
Data Index: 295319 (Open Web Text)
Max Activating Token Index: 248
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.8409. Min Range: -5.8409
Max Act: 5.6221. Min Act: -0.1700
Data Index: 295317 (Open Web Text)
Max Activating Token Index: 899
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.8409. Min Range: -5.8409
Max Act: 5.5284. Min Act: -0.1700
Data Index: 3984361 (Open Web Text)
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.8409. Min Range: -5.8409
Max Act: 5.4971. Min Act: -0.1700
Data Index: 7622262 (Open Web Text)
Max Activating Token Index: 791
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.8409. Min Range: -5.8409
Max Act: 5.3721. Min Act: -0.1700
Data Index: 8305555 (Open Web Text)
Max Activating Token Index: 1014
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.8409. Min Range: -5.8409
Max Act: 5.4034. Min Act: -0.1700
Data Index: 5673283 (Open Web Text)
Max Activating Token Index: 204
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.8409. Min Range: -5.8409
Max Act: 5.4034. Min Act: -0.1700
Data Index: 2768993 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.8409. Min Range: -5.8409
Max Act: 5.3721. Min Act: -0.1700
Data Index: 1683904 (Open Web Text)
Max Activating Token Index: 78
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.8409. Min Range: -5.8409
Max Act: 5.3721. Min Act: -0.1700
Data Index: 3948961 (Open Web Text)
Max Activating Token Index: 469
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.8409. Min Range: -5.8409
Max Act: 5.3721. Min Act: -0.1700
Data Index: 2784667 (Open Web Text)
Max Activating Token Index: 350
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.8409. Min Range: -5.8409
Max Act: 5.3409. Min Act: -0.1700
Data Index: 6250735 (Open Web Text)
Max Activating Token Index: 203
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.8409. Min Range: -5.8409
Max Act: 5.3409. Min Act: -0.1700
Data Index: 6573515 (Open Web Text)
Max Activating Token Index: 715
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.8409. Min Range: -5.8409
Max Act: 5.3409. Min Act: -0.1700
Data Index: 5093797 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.8409. Min Range: -5.8409
Max Act: 5.3096. Min Act: -0.1700
Data Index: 6164725 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.8409. Min Range: -5.8409
Max Act: 5.3409. Min Act: -0.1700
Data Index: 4249010 (Open Web Text)
Max Activating Token Index: 870
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.8409. Min Range: -5.8409
Max Act: 5.3096. Min Act: -0.1700
Data Index: 1686769 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #19