Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2219 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.7350. Min Range: -5.7350
Max Act: 5.7350. Min Act: -0.1700
Data Index: 4788562 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.7350. Min Range: -5.7350
Max Act: 5.6412. Min Act: -0.1700
Data Index: 1918919 (Open Web Text)
Max Activating Token Index: 314
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.7350. Min Range: -5.7350
Max Act: 5.5162. Min Act: -0.1700
Data Index: 1402698 (Open Web Text)
Max Activating Token Index: 945
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.7350. Min Range: -5.7350
Max Act: 5.4850. Min Act: -0.1700
Data Index: 3247520 (Open Web Text)
Max Activating Token Index: 129
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.7350. Min Range: -5.7350
Max Act: 5.4225. Min Act: -0.1700
Data Index: 1710773 (Open Web Text)
Max Activating Token Index: 75
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.7350. Min Range: -5.7350
Max Act: 5.3912. Min Act: -0.1700
Data Index: 3386227 (Open Web Text)
Max Activating Token Index: 277
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.7350. Min Range: -5.7350
Max Act: 5.3912. Min Act: -0.1700
Data Index: 1197734 (Open Web Text)
Max Activating Token Index: 122
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.7350. Min Range: -5.7350
Max Act: 5.3600. Min Act: -0.1700
Data Index: 6357258 (Open Web Text)
Max Activating Token Index: 110
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.7350. Min Range: -5.7350
Max Act: 5.3600. Min Act: -0.1700
Data Index: 1374917 (Open Web Text)
Max Activating Token Index: 459
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.7350. Min Range: -5.7350
Max Act: 5.3287. Min Act: -0.1700
Data Index: 6307109 (Open Web Text)
Max Activating Token Index: 723
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.7350. Min Range: -5.7350
Max Act: 5.2975. Min Act: -0.1700
Data Index: 4920562 (Open Web Text)
Max Activating Token Index: 317
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.7350. Min Range: -5.7350
Max Act: 5.2037. Min Act: -0.1700
Data Index: 4898591 (Open Web Text)
Max Activating Token Index: 373
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.7350. Min Range: -5.7350
Max Act: 5.2350. Min Act: -0.1700
Data Index: 7322546 (Open Web Text)
Max Activating Token Index: 662
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.7350. Min Range: -5.7350
Max Act: 5.1725. Min Act: -0.1700
Data Index: 5814461 (Open Web Text)
Max Activating Token Index: 316
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.7350. Min Range: -5.7350
Max Act: 5.1725. Min Act: -0.1700
Data Index: 7211293 (Open Web Text)
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.7350. Min Range: -5.7350
Max Act: 5.1725. Min Act: -0.1700
Data Index: 510095 (Open Web Text)
Max Activating Token Index: 686
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.7350. Min Range: -5.7350
Max Act: 5.1725. Min Act: -0.1700
Data Index: 2802662 (Open Web Text)
Max Activating Token Index: 176
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.7350. Min Range: -5.7350
Max Act: 5.1725. Min Act: -0.1700
Data Index: 10369 (Open Web Text)
Max Activating Token Index: 497
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.7350. Min Range: -5.7350
Max Act: 5.1725. Min Act: -0.1700
Data Index: 3705283 (Open Web Text)
Max Activating Token Index: 340
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.7350. Min Range: -5.7350
Max Act: 5.1725. Min Act: -0.1700
Data Index: 7504895 (Open Web Text)
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #19