Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3359 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.9433. Min Range: -7.9433
Max Act: 7.9433. Min Act: -0.1700
Data Index: 5549150 (Open Web Text)
Max Activating Token Index: 334
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.9433. Min Range: -7.9433
Max Act: 7.7558. Min Act: -0.1700
Data Index: 5883386 (Open Web Text)
Max Activating Token Index: 256
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.9433. Min Range: -7.9433
Max Act: 7.7246. Min Act: -0.1700
Data Index: 8082845 (Open Web Text)
Max Activating Token Index: 310
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.9433. Min Range: -7.9433
Max Act: 7.7246. Min Act: -0.1700
Data Index: 4889427 (Open Web Text)
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.9433. Min Range: -7.9433
Max Act: 7.6621. Min Act: -0.1700
Data Index: 8497433 (Open Web Text)
Max Activating Token Index: 787
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.9433. Min Range: -7.9433
Max Act: 7.6308. Min Act: -0.1700
Data Index: 7707658 (Open Web Text)
Max Activating Token Index: 809
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.9433. Min Range: -7.9433
Max Act: 7.6621. Min Act: -0.1700
Data Index: 7777379 (Open Web Text)
Max Activating Token Index: 892
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.9433. Min Range: -7.9433
Max Act: 7.6621. Min Act: -0.1700
Data Index: 1715296 (Open Web Text)
Max Activating Token Index: 653
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.9433. Min Range: -7.9433
Max Act: 7.6621. Min Act: -0.1700
Data Index: 5622602 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.9433. Min Range: -7.9433
Max Act: 7.6308. Min Act: -0.1700
Data Index: 720073 (Open Web Text)
Max Activating Token Index: 198
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.9433. Min Range: -7.9433
Max Act: 7.5996. Min Act: -0.1700
Data Index: 8204511 (Open Web Text)
Max Activating Token Index: 141
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.9433. Min Range: -7.9433
Max Act: 7.5371. Min Act: -0.1700
Data Index: 8323488 (Open Web Text)
Max Activating Token Index: 295
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.9433. Min Range: -7.9433
Max Act: 7.5371. Min Act: -0.1700
Data Index: 3769322 (Open Web Text)
Max Activating Token Index: 375
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.9433. Min Range: -7.9433
Max Act: 7.5371. Min Act: -0.1700
Data Index: 1887096 (Open Web Text)
Max Activating Token Index: 820
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.9433. Min Range: -7.9433
Max Act: 7.5371. Min Act: -0.1700
Data Index: 8780959 (Open Web Text)
Max Activating Token Index: 142
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.9433. Min Range: -7.9433
Max Act: 7.5371. Min Act: -0.1700
Data Index: 4874407 (Open Web Text)
Max Activating Token Index: 527
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.9433. Min Range: -7.9433
Max Act: 7.5371. Min Act: -0.1700
Data Index: 5677020 (Open Web Text)
Max Activating Token Index: 914
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.9433. Min Range: -7.9433
Max Act: 7.5058. Min Act: -0.1700
Data Index: 2891412 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.9433. Min Range: -7.9433
Max Act: 7.5058. Min Act: -0.1700
Data Index: 6605557 (Open Web Text)
Max Activating Token Index: 866
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.9433. Min Range: -7.9433
Max Act: 7.5058. Min Act: -0.1700
Data Index: 6442463 (Open Web Text)
Max Activating Token Index: 933
Click toggle to see full text
Truncated
Full Text #19