Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3661 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.5404. Min Range: -5.5404
Max Act: 5.5404. Min Act: -0.1700
Data Index: 8255743 (Open Web Text)
Max Activating Token Index: 484
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.5404. Min Range: -5.5404
Max Act: 5.4779. Min Act: -0.1700
Data Index: 8419030 (Open Web Text)
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.5404. Min Range: -5.5404
Max Act: 5.4779. Min Act: -0.1700
Data Index: 436025 (Open Web Text)
Max Activating Token Index: 669
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.5404. Min Range: -5.5404
Max Act: 5.4154. Min Act: -0.1700
Data Index: 4182062 (Open Web Text)
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.5404. Min Range: -5.5404
Max Act: 5.3217. Min Act: -0.1700
Data Index: 1948403 (Open Web Text)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.5404. Min Range: -5.5404
Max Act: 5.2592. Min Act: -0.1700
Data Index: 872898 (Open Web Text)
Max Activating Token Index: 362
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.5404. Min Range: -5.5404
Max Act: 5.2592. Min Act: -0.1700
Data Index: 1948413 (Open Web Text)
Max Activating Token Index: 263
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.5404. Min Range: -5.5404
Max Act: 5.2279. Min Act: -0.1700
Data Index: 4168145 (Open Web Text)
Max Activating Token Index: 565
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.5404. Min Range: -5.5404
Max Act: 5.1967. Min Act: -0.1700
Data Index: 4457730 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.5404. Min Range: -5.5404
Max Act: 5.1967. Min Act: -0.1700
Data Index: 504305 (Open Web Text)
Max Activating Token Index: 607
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.5404. Min Range: -5.5404
Max Act: 5.1654. Min Act: -0.1700
Data Index: 4168139 (Open Web Text)
Max Activating Token Index: 432
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.5404. Min Range: -5.5404
Max Act: 5.1342. Min Act: -0.1700
Data Index: 560382 (Open Web Text)
Max Activating Token Index: 451
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.5404. Min Range: -5.5404
Max Act: 5.0717. Min Act: -0.1700
Data Index: 5657250 (Open Web Text)
Max Activating Token Index: 997
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.5404. Min Range: -5.5404
Max Act: 5.1342. Min Act: -0.1700
Data Index: 3781493 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.5404. Min Range: -5.5404
Max Act: 5.0717. Min Act: -0.1700
Data Index: 7176527 (Open Web Text)
Max Activating Token Index: 280
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.5404. Min Range: -5.5404
Max Act: 5.0717. Min Act: -0.1700
Data Index: 3800473 (Open Web Text)
Max Activating Token Index: 187
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.5404. Min Range: -5.5404
Max Act: 5.0404. Min Act: -0.1700
Data Index: 3175967 (Open Web Text)
Max Activating Token Index: 670
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.5404. Min Range: -5.5404
Max Act: 5.0404. Min Act: -0.1700
Data Index: 2796143 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.5404. Min Range: -5.5404
Max Act: 5.0404. Min Act: -0.1700
Data Index: 2221134 (Open Web Text)
Max Activating Token Index: 254
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.5404. Min Range: -5.5404
Max Act: 5.0404. Min Act: -0.1700
Data Index: 2250806 (Open Web Text)
Max Activating Token Index: 565
Click toggle to see full text
Truncated
Full Text #19