Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5291 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 13.9382. Min Range: -13.9382
Max Act: 13.9382. Min Act: -0.1700
Data Index: 1339989 (Open Web Text)
Max Activating Token Index: 565
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 13.9382. Min Range: -13.9382
Max Act: 13.8132. Min Act: -0.1700
Data Index: 8478083 (Open Web Text)
Max Activating Token Index: 787
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 13.9382. Min Range: -13.9382
Max Act: 13.7507. Min Act: -0.1700
Data Index: 3088045 (Open Web Text)
Max Activating Token Index: 210
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 13.9382. Min Range: -13.9382
Max Act: 13.5632. Min Act: -0.1700
Data Index: 3146310 (Open Web Text)
Max Activating Token Index: 504
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 13.9382. Min Range: -13.9382
Max Act: 13.5007. Min Act: -0.1700
Data Index: 4602540 (Open Web Text)
Max Activating Token Index: 247
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 13.9382. Min Range: -13.9382
Max Act: 13.4382. Min Act: -0.1700
Data Index: 6954084 (Open Web Text)
Max Activating Token Index: 123
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 13.9382. Min Range: -13.9382
Max Act: 13.3757. Min Act: -0.1700
Data Index: 8176635 (Open Web Text)
Max Activating Token Index: 281
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 13.9382. Min Range: -13.9382
Max Act: 13.4382. Min Act: -0.1699
Data Index: 8618577 (Open Web Text)
Max Activating Token Index: 160
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 13.9382. Min Range: -13.9382
Max Act: 13.3757. Min Act: -0.1700
Data Index: 6738133 (Open Web Text)
Max Activating Token Index: 768
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 13.9382. Min Range: -13.9382
Max Act: 13.3132. Min Act: -0.1700
Data Index: 1533845 (Open Web Text)
Max Activating Token Index: 902
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 13.9382. Min Range: -13.9382
Max Act: 13.3132. Min Act: -0.1697
Data Index: 6603473 (Open Web Text)
Max Activating Token Index: 902
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 13.9382. Min Range: -13.9382
Max Act: 13.3132. Min Act: -0.1700
Data Index: 3142675 (Open Web Text)
Max Activating Token Index: 604
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 13.9382. Min Range: -13.9382
Max Act: 13.3757. Min Act: -0.1700
Data Index: 3084781 (Open Web Text)
Max Activating Token Index: 646
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 13.9382. Min Range: -13.9382
Max Act: 13.2507. Min Act: -0.1700
Data Index: 8986 (Open Web Text)
Max Activating Token Index: 157
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 13.9382. Min Range: -13.9382
Max Act: 13.1882. Min Act: -0.1700
Data Index: 1426683 (Open Web Text)
Max Activating Token Index: 657
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 13.9382. Min Range: -13.9382
Max Act: 13.2507. Min Act: -0.1700
Data Index: 4496828 (Open Web Text)
Max Activating Token Index: 622
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 13.9382. Min Range: -13.9382
Max Act: 13.2507. Min Act: -0.1700
Data Index: 7751412 (Open Web Text)
Max Activating Token Index: 401
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 13.9382. Min Range: -13.9382
Max Act: 13.2507. Min Act: -0.1700
Data Index: 3030045 (Open Web Text)
Max Activating Token Index: 899
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 13.9382. Min Range: -13.9382
Max Act: 13.2507. Min Act: -0.1700
Data Index: 4138606 (Open Web Text)
Max Activating Token Index: 982
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 13.9382. Min Range: -13.9382
Max Act: 13.1882. Min Act: -0.1700
Data Index: 39562 (Open Web Text)
Max Activating Token Index: 391
Click toggle to see full text
Truncated
Full Text #19