Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1958 in Layer 27
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.5445. Min Range: -6.5445
Max Act: 6.5445. Min Act: -0.1700
Data Index: 4933455 (Open Web Text)
Max Activating Token Index: 506
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.5445. Min Range: -6.5445
Max Act: 6.5133. Min Act: -0.1700
Data Index: 2669661 (Open Web Text)
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.5445. Min Range: -6.5445
Max Act: 6.4195. Min Act: -0.1700
Data Index: 6501925 (Open Web Text)
Max Activating Token Index: 515
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.5445. Min Range: -6.5445
Max Act: 6.4508. Min Act: -0.1700
Data Index: 4650088 (Open Web Text)
Max Activating Token Index: 898
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.5445. Min Range: -6.5445
Max Act: 6.3883. Min Act: -0.1700
Data Index: 4037632 (Open Web Text)
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.5445. Min Range: -6.5445
Max Act: 6.3883. Min Act: -0.1700
Data Index: 2382801 (Open Web Text)
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.5445. Min Range: -6.5445
Max Act: 6.2945. Min Act: -0.1700
Data Index: 5902532 (Open Web Text)
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.5445. Min Range: -6.5445
Max Act: 6.2320. Min Act: -0.1700
Data Index: 3129451 (Open Web Text)
Max Activating Token Index: 990
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.5445. Min Range: -6.5445
Max Act: 6.2008. Min Act: -0.1700
Data Index: 7368876 (Open Web Text)
Max Activating Token Index: 1014
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.5445. Min Range: -6.5445
Max Act: 6.2008. Min Act: -0.1700
Data Index: 836757 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.5445. Min Range: -6.5445
Max Act: 6.1695. Min Act: -0.1700
Data Index: 1379947 (Open Web Text)
Max Activating Token Index: 677
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.5445. Min Range: -6.5445
Max Act: 6.1695. Min Act: -0.1700
Data Index: 6297006 (Open Web Text)
Max Activating Token Index: 636
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.5445. Min Range: -6.5445
Max Act: 6.1383. Min Act: -0.1700
Data Index: 580156 (Open Web Text)
Max Activating Token Index: 852
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.5445. Min Range: -6.5445
Max Act: 6.1070. Min Act: -0.1700
Data Index: 5631011 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.5445. Min Range: -6.5445
Max Act: 6.0758. Min Act: -0.1700
Data Index: 4594405 (Open Web Text)
Max Activating Token Index: 1013
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.5445. Min Range: -6.5445
Max Act: 6.0758. Min Act: -0.1700
Data Index: 4296151 (Open Web Text)
Max Activating Token Index: 432
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.5445. Min Range: -6.5445
Max Act: 6.0758. Min Act: -0.1700
Data Index: 3224357 (Open Web Text)
Max Activating Token Index: 848
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.5445. Min Range: -6.5445
Max Act: 6.0445. Min Act: -0.1700
Data Index: 4859163 (Open Web Text)
Max Activating Token Index: 111
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.5445. Min Range: -6.5445
Max Act: 6.0445. Min Act: -0.1700
Data Index: 6885837 (Open Web Text)
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.5445. Min Range: -6.5445
Max Act: 6.0445. Min Act: -0.1700
Data Index: 142628 (Open Web Text)
Max Activating Token Index: 628
Click toggle to see full text
Truncated
Full Text #19