Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 29 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.5854. Min Range: -4.5854
Max Act: 4.5854. Min Act: -0.1700
Data Index: 1060771 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.5854. Min Range: -4.5854
Max Act: 4.5542. Min Act: -0.1700
Data Index: 3393151 (Open Web Text)
Max Activating Token Index: 320
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.5854. Min Range: -4.5854
Max Act: 4.5229. Min Act: -0.1700
Data Index: 5244037 (Open Web Text)
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.5854. Min Range: -4.5854
Max Act: 4.4917. Min Act: -0.1700
Data Index: 8295103 (Open Web Text)
Max Activating Token Index: 384
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.5854. Min Range: -4.5854
Max Act: 4.4917. Min Act: -0.1700
Data Index: 905315 (Open Web Text)
Max Activating Token Index: 677
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.5854. Min Range: -4.5854
Max Act: 4.4917. Min Act: -0.1700
Data Index: 3513980 (Open Web Text)
Max Activating Token Index: 856
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.5854. Min Range: -4.5854
Max Act: 4.4604. Min Act: -0.1700
Data Index: 7001447 (Open Web Text)
Max Activating Token Index: 479
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.5854. Min Range: -4.5854
Max Act: 4.4604. Min Act: -0.1700
Data Index: 3894988 (Open Web Text)
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.5854. Min Range: -4.5854
Max Act: 4.4292. Min Act: -0.1700
Data Index: 554788 (Open Web Text)
Max Activating Token Index: 528
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.5854. Min Range: -4.5854
Max Act: 4.4292. Min Act: -0.1700
Data Index: 4249703 (Open Web Text)
Max Activating Token Index: 260
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.5854. Min Range: -4.5854
Max Act: 4.4292. Min Act: -0.1700
Data Index: 3706679 (Open Web Text)
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.5854. Min Range: -4.5854
Max Act: 4.4604. Min Act: -0.1700
Data Index: 5999192 (Open Web Text)
Max Activating Token Index: 955
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.5854. Min Range: -4.5854
Max Act: 4.4292. Min Act: -0.1700
Data Index: 350089 (Open Web Text)
Max Activating Token Index: 381
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.5854. Min Range: -4.5854
Max Act: 4.3979. Min Act: -0.1700
Data Index: 822366 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.5854. Min Range: -4.5854
Max Act: 4.3979. Min Act: -0.1700
Data Index: 5997092 (Open Web Text)
Max Activating Token Index: 189
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.5854. Min Range: -4.5854
Max Act: 4.4292. Min Act: -0.1700
Data Index: 8476692 (Open Web Text)
Max Activating Token Index: 68
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.5854. Min Range: -4.5854
Max Act: 4.3979. Min Act: -0.1700
Data Index: 139713 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.5854. Min Range: -4.5854
Max Act: 4.3667. Min Act: -0.1700
Data Index: 5999193 (Open Web Text)
Max Activating Token Index: 379
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.5854. Min Range: -4.5854
Max Act: 4.3667. Min Act: -0.1700
Data Index: 7118302 (Open Web Text)
Max Activating Token Index: 625
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.5854. Min Range: -4.5854
Max Act: 4.3667. Min Act: -0.1700
Data Index: 8323163 (Open Web Text)
Max Activating Token Index: 478
Click toggle to see full text
Truncated
Full Text #19