Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2956 in Layer 43
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.2301. Min Range: -7.2301
Max Act: 7.2301. Min Act: -0.1700
Data Index: 7637842 (Open Web Text)
Max Activating Token Index: 206
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.2301. Min Range: -7.2301
Max Act: 7.0739. Min Act: -0.1700
Data Index: 6591859 (Open Web Text)
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.2301. Min Range: -7.2301
Max Act: 7.0426. Min Act: -0.1700
Data Index: 1430717 (Open Web Text)
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.2301. Min Range: -7.2301
Max Act: 7.0426. Min Act: -0.1700
Data Index: 4751138 (Open Web Text)
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.2301. Min Range: -7.2301
Max Act: 7.0426. Min Act: -0.1700
Data Index: 3799920 (Open Web Text)
Max Activating Token Index: 747
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.2301. Min Range: -7.2301
Max Act: 7.0114. Min Act: -0.1700
Data Index: 7876185 (Open Web Text)
Max Activating Token Index: 439
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.2301. Min Range: -7.2301
Max Act: 7.0114. Min Act: -0.1700
Data Index: 45256 (Open Web Text)
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.2301. Min Range: -7.2301
Max Act: 6.9489. Min Act: -0.1700
Data Index: 1834626 (Open Web Text)
Max Activating Token Index: 449
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.2301. Min Range: -7.2301
Max Act: 6.9176. Min Act: -0.1700
Data Index: 347178 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.2301. Min Range: -7.2301
Max Act: 6.9801. Min Act: -0.1700
Data Index: 776883 (Open Web Text)
Max Activating Token Index: 395
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.2301. Min Range: -7.2301
Max Act: 6.9489. Min Act: -0.1700
Data Index: 6119134 (Open Web Text)
Max Activating Token Index: 38
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.2301. Min Range: -7.2301
Max Act: 6.9489. Min Act: -0.1700
Data Index: 3573552 (Open Web Text)
Max Activating Token Index: 325
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.2301. Min Range: -7.2301
Max Act: 6.9176. Min Act: -0.1700
Data Index: 6343257 (Open Web Text)
Max Activating Token Index: 183
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.2301. Min Range: -7.2301
Max Act: 6.9176. Min Act: -0.1700
Data Index: 6151350 (Open Web Text)
Max Activating Token Index: 185
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.2301. Min Range: -7.2301
Max Act: 6.9176. Min Act: -0.1700
Data Index: 4751126 (Open Web Text)
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.2301. Min Range: -7.2301
Max Act: 6.8864. Min Act: -0.1700
Data Index: 554235 (Open Web Text)
Max Activating Token Index: 469
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.2301. Min Range: -7.2301
Max Act: 6.8551. Min Act: -0.1700
Data Index: 4124445 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.2301. Min Range: -7.2301
Max Act: 6.8239. Min Act: -0.1700
Data Index: 5610190 (Open Web Text)
Max Activating Token Index: 876
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.2301. Min Range: -7.2301
Max Act: 6.8551. Min Act: -0.1700
Data Index: 6952358 (Open Web Text)
Max Activating Token Index: 646
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.2301. Min Range: -7.2301
Max Act: 6.8551. Min Act: -0.1700
Data Index: 409537 (Open Web Text)
Max Activating Token Index: 48
Click toggle to see full text
Truncated
Full Text #19