Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3475 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.7363. Min Range: -4.7363
Max Act: 4.7363. Min Act: -0.1700
Data Index: 5641613 (Open Web Text)
Max Activating Token Index: 877
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.7363. Min Range: -4.7363
Max Act: 4.6426. Min Act: -0.1700
Data Index: 8173606 (Open Web Text)
Max Activating Token Index: 890
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.7363. Min Range: -4.7363
Max Act: 4.6426. Min Act: -0.1700
Data Index: 5387592 (Open Web Text)
Max Activating Token Index: 755
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.7363. Min Range: -4.7363
Max Act: 4.5801. Min Act: -0.1700
Data Index: 6999799 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.7363. Min Range: -4.7363
Max Act: 4.5801. Min Act: -0.1700
Data Index: 8312072 (Open Web Text)
Max Activating Token Index: 939
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.7363. Min Range: -4.7363
Max Act: 4.5176. Min Act: -0.1700
Data Index: 2954267 (Open Web Text)
Max Activating Token Index: 259
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.7363. Min Range: -4.7363
Max Act: 4.5176. Min Act: -0.1700
Data Index: 578438 (Open Web Text)
Max Activating Token Index: 451
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.7363. Min Range: -4.7363
Max Act: 4.5176. Min Act: -0.1700
Data Index: 3886129 (Open Web Text)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.7363. Min Range: -4.7363
Max Act: 4.4863. Min Act: -0.1700
Data Index: 2455943 (Open Web Text)
Max Activating Token Index: 368
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.7363. Min Range: -4.7363
Max Act: 4.4863. Min Act: -0.1700
Data Index: 4225052 (Open Web Text)
Max Activating Token Index: 421
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.7363. Min Range: -4.7363
Max Act: 4.4551. Min Act: -0.1700
Data Index: 2005630 (Open Web Text)
Max Activating Token Index: 783
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.7363. Min Range: -4.7363
Max Act: 4.4551. Min Act: -0.1700
Data Index: 5864094 (Open Web Text)
Max Activating Token Index: 566
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.7363. Min Range: -4.7363
Max Act: 4.4551. Min Act: -0.1700
Data Index: 6863259 (Open Web Text)
Max Activating Token Index: 38
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.7363. Min Range: -4.7363
Max Act: 4.4238. Min Act: -0.1700
Data Index: 5775323 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.7363. Min Range: -4.7363
Max Act: 4.4238. Min Act: -0.1700
Data Index: 6998305 (Open Web Text)
Max Activating Token Index: 169
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.7363. Min Range: -4.7363
Max Act: 4.3926. Min Act: -0.1700
Data Index: 7445861 (Open Web Text)
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.7363. Min Range: -4.7363
Max Act: 4.3926. Min Act: -0.1700
Data Index: 8795225 (Open Web Text)
Max Activating Token Index: 69
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.7363. Min Range: -4.7363
Max Act: 4.3926. Min Act: -0.1700
Data Index: 8559424 (Open Web Text)
Max Activating Token Index: 405
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.7363. Min Range: -4.7363
Max Act: 4.3613. Min Act: -0.1700
Data Index: 289663 (Open Web Text)
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.7363. Min Range: -4.7363
Max Act: 4.3926. Min Act: -0.1700
Data Index: 313051 (Open Web Text)
Max Activating Token Index: 434
Click toggle to see full text
Truncated
Full Text #19