Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3536 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.6296. Min Range: -4.6296
Max Act: 4.6296. Min Act: -0.1700
Data Index: 1275154 (Open Web Text)
Max Activating Token Index: 334
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.6296. Min Range: -4.6296
Max Act: 4.5671. Min Act: -0.1700
Data Index: 1275123 (Open Web Text)
Max Activating Token Index: 662
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.6296. Min Range: -4.6296
Max Act: 4.5671. Min Act: -0.1700
Data Index: 1275145 (Open Web Text)
Max Activating Token Index: 438
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.6296. Min Range: -4.6296
Max Act: 4.5671. Min Act: -0.1700
Data Index: 1275144 (Open Web Text)
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.6296. Min Range: -4.6296
Max Act: 4.5671. Min Act: -0.1700
Data Index: 1275143 (Open Web Text)
Max Activating Token Index: 318
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.6296. Min Range: -4.6296
Max Act: 4.5359. Min Act: -0.1700
Data Index: 1275130 (Open Web Text)
Max Activating Token Index: 369
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.6296. Min Range: -4.6296
Max Act: 4.5046. Min Act: -0.1700
Data Index: 1275147 (Open Web Text)
Max Activating Token Index: 951
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.6296. Min Range: -4.6296
Max Act: 4.5359. Min Act: -0.1700
Data Index: 8459906 (Open Web Text)
Max Activating Token Index: 368
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.6296. Min Range: -4.6296
Max Act: 4.5359. Min Act: -0.1700
Data Index: 4975686 (Open Web Text)
Max Activating Token Index: 391
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.6296. Min Range: -4.6296
Max Act: 4.5046. Min Act: -0.1700
Data Index: 1275156 (Open Web Text)
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.6296. Min Range: -4.6296
Max Act: 4.5046. Min Act: -0.1700
Data Index: 5595718 (Open Web Text)
Max Activating Token Index: 804
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.6296. Min Range: -4.6296
Max Act: 4.5046. Min Act: -0.1700
Data Index: 163301 (Open Web Text)
Max Activating Token Index: 642
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.6296. Min Range: -4.6296
Max Act: 4.4734. Min Act: -0.1700
Data Index: 5850828 (Open Web Text)
Max Activating Token Index: 759
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.6296. Min Range: -4.6296
Max Act: 4.4734. Min Act: -0.1700
Data Index: 6176439 (Open Web Text)
Max Activating Token Index: 44
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.6296. Min Range: -4.6296
Max Act: 4.4734. Min Act: -0.1700
Data Index: 1275127 (Open Web Text)
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.6296. Min Range: -4.6296
Max Act: 4.4421. Min Act: -0.1700
Data Index: 8110183 (Open Web Text)
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.6296. Min Range: -4.6296
Max Act: 4.4109. Min Act: -0.1700
Data Index: 1275150 (Open Web Text)
Max Activating Token Index: 449
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.6296. Min Range: -4.6296
Max Act: 4.4109. Min Act: -0.1700
Data Index: 2727836 (Open Web Text)
Max Activating Token Index: 564
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.6296. Min Range: -4.6296
Max Act: 4.4109. Min Act: -0.1700
Data Index: 5070157 (Open Web Text)
Max Activating Token Index: 530
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.6296. Min Range: -4.6296
Max Act: 4.4109. Min Act: -0.1700
Data Index: 7953053 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #19