Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2759 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.0280. Min Range: -7.0280
Max Act: 7.0280. Min Act: -0.1700
Data Index: 1700988 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.0280. Min Range: -7.0280
Max Act: 6.9967. Min Act: -0.1700
Data Index: 7167972 (Open Web Text)
Max Activating Token Index: 892
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.0280. Min Range: -7.0280
Max Act: 6.9342. Min Act: -0.1700
Data Index: 6462294 (Open Web Text)
Max Activating Token Index: 438
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.0280. Min Range: -7.0280
Max Act: 6.8405. Min Act: -0.1700
Data Index: 2068246 (Open Web Text)
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.0280. Min Range: -7.0280
Max Act: 6.9030. Min Act: -0.1700
Data Index: 5038769 (Open Web Text)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.0280. Min Range: -7.0280
Max Act: 6.8092. Min Act: -0.1700
Data Index: 8252558 (Open Web Text)
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.0280. Min Range: -7.0280
Max Act: 6.6530. Min Act: -0.1700
Data Index: 7859659 (Open Web Text)
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.0280. Min Range: -7.0280
Max Act: 6.5592. Min Act: -0.1700
Data Index: 2064839 (Open Web Text)
Max Activating Token Index: 518
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.0280. Min Range: -7.0280
Max Act: 6.5592. Min Act: -0.1700
Data Index: 7673758 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.0280. Min Range: -7.0280
Max Act: 6.5280. Min Act: -0.1700
Data Index: 4541726 (Open Web Text)
Max Activating Token Index: 677
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.0280. Min Range: -7.0280
Max Act: 6.5905. Min Act: -0.1700
Data Index: 465717 (Open Web Text)
Max Activating Token Index: 960
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.0280. Min Range: -7.0280
Max Act: 6.4967. Min Act: -0.1700
Data Index: 8107022 (Open Web Text)
Max Activating Token Index: 504
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.0280. Min Range: -7.0280
Max Act: 6.4967. Min Act: -0.1700
Data Index: 7811770 (Open Web Text)
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.0280. Min Range: -7.0280
Max Act: 6.4967. Min Act: -0.1700
Data Index: 2661204 (Open Web Text)
Max Activating Token Index: 83
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.0280. Min Range: -7.0280
Max Act: 6.4342. Min Act: -0.1700
Data Index: 1264549 (Open Web Text)
Max Activating Token Index: 180
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.0280. Min Range: -7.0280
Max Act: 6.4342. Min Act: -0.1700
Data Index: 2621880 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.0280. Min Range: -7.0280
Max Act: 6.4342. Min Act: -0.1700
Data Index: 5665511 (Open Web Text)
Max Activating Token Index: 660
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.0280. Min Range: -7.0280
Max Act: 6.4342. Min Act: -0.1700
Data Index: 3812840 (Open Web Text)
Max Activating Token Index: 1010
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.0280. Min Range: -7.0280
Max Act: 6.4030. Min Act: -0.1700
Data Index: 1634513 (Open Web Text)
Max Activating Token Index: 36
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.0280. Min Range: -7.0280
Max Act: 6.3717. Min Act: -0.1700
Data Index: 4504376 (Open Web Text)
Max Activating Token Index: 690
Click toggle to see full text
Truncated
Full Text #19