Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3016 in Layer 38
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.0530. Min Range: -7.0530
Max Act: 7.0530. Min Act: -0.1700
Data Index: 348690 (Open Web Text)
Max Activating Token Index: 203
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.0530. Min Range: -7.0530
Max Act: 6.8655. Min Act: -0.1700
Data Index: 106935 (Open Web Text)
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.0530. Min Range: -7.0530
Max Act: 6.5217. Min Act: -0.1700
Data Index: 1295771 (Open Web Text)
Max Activating Token Index: 809
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.0530. Min Range: -7.0530
Max Act: 6.4905. Min Act: -0.1700
Data Index: 8590895 (Open Web Text)
Max Activating Token Index: 234
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.0530. Min Range: -7.0530
Max Act: 6.4592. Min Act: -0.1700
Data Index: 5163569 (Open Web Text)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.0530. Min Range: -7.0530
Max Act: 6.4280. Min Act: -0.1700
Data Index: 190444 (Open Web Text)
Max Activating Token Index: 809
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.0530. Min Range: -7.0530
Max Act: 6.4280. Min Act: -0.1700
Data Index: 7205046 (Open Web Text)
Max Activating Token Index: 674
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.0530. Min Range: -7.0530
Max Act: 6.3967. Min Act: -0.1700
Data Index: 2878678 (Open Web Text)
Max Activating Token Index: 990
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.0530. Min Range: -7.0530
Max Act: 6.3967. Min Act: -0.1700
Data Index: 3298960 (Open Web Text)
Max Activating Token Index: 666
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.0530. Min Range: -7.0530
Max Act: 6.4280. Min Act: -0.1700
Data Index: 6390278 (Open Web Text)
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.0530. Min Range: -7.0530
Max Act: 6.3655. Min Act: -0.1700
Data Index: 1998634 (Open Web Text)
Max Activating Token Index: 77
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.0530. Min Range: -7.0530
Max Act: 6.3342. Min Act: -0.1700
Data Index: 3105994 (Open Web Text)
Max Activating Token Index: 645
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.0530. Min Range: -7.0530
Max Act: 6.3342. Min Act: -0.1700
Data Index: 6612472 (Open Web Text)
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.0530. Min Range: -7.0530
Max Act: 6.3342. Min Act: -0.1700
Data Index: 4350633 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.0530. Min Range: -7.0530
Max Act: 6.3342. Min Act: -0.1700
Data Index: 5885144 (Open Web Text)
Max Activating Token Index: 839
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.0530. Min Range: -7.0530
Max Act: 6.3030. Min Act: -0.1700
Data Index: 6946238 (Open Web Text)
Max Activating Token Index: 724
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.0530. Min Range: -7.0530
Max Act: 6.3030. Min Act: -0.1700
Data Index: 1592492 (Open Web Text)
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.0530. Min Range: -7.0530
Max Act: 6.3030. Min Act: -0.1700
Data Index: 5102316 (Open Web Text)
Max Activating Token Index: 716
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.0530. Min Range: -7.0530
Max Act: 6.2717. Min Act: -0.1700
Data Index: 8527678 (Open Web Text)
Max Activating Token Index: 459
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.0530. Min Range: -7.0530
Max Act: 6.2405. Min Act: -0.1700
Data Index: 3534467 (Open Web Text)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #19