Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3641 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 11.9632. Min Range: -11.9632
Max Act: 11.9632. Min Act: -0.1700
Data Index: 4913936 (Open Web Text)
Max Activating Token Index: 319
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 11.9632. Min Range: -11.9632
Max Act: 11.2757. Min Act: -0.1700
Data Index: 2579229 (Open Web Text)
Max Activating Token Index: 308
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 11.9632. Min Range: -11.9632
Max Act: 11.2757. Min Act: -0.1700
Data Index: 3534455 (Open Web Text)
Max Activating Token Index: 322
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 11.9632. Min Range: -11.9632
Max Act: 11.1507. Min Act: -0.1700
Data Index: 8032086 (Open Web Text)
Max Activating Token Index: 608
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 11.9632. Min Range: -11.9632
Max Act: 11.2132. Min Act: -0.1700
Data Index: 1885666 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 11.9632. Min Range: -11.9632
Max Act: 10.9632. Min Act: -0.1700
Data Index: 7057158 (Open Web Text)
Max Activating Token Index: 978
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 11.9632. Min Range: -11.9632
Max Act: 11.0257. Min Act: -0.1700
Data Index: 164592 (Open Web Text)
Max Activating Token Index: 299
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 11.9632. Min Range: -11.9632
Max Act: 10.9007. Min Act: -0.1700
Data Index: 4489474 (Open Web Text)
Max Activating Token Index: 1014
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 11.9632. Min Range: -11.9632
Max Act: 10.9007. Min Act: -0.1700
Data Index: 7981754 (Open Web Text)
Max Activating Token Index: 952
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 11.9632. Min Range: -11.9632
Max Act: 10.8382. Min Act: -0.1700
Data Index: 705576 (Open Web Text)
Max Activating Token Index: 247
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 11.9632. Min Range: -11.9632
Max Act: 10.8382. Min Act: -0.1700
Data Index: 4153422 (Open Web Text)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 11.9632. Min Range: -11.9632
Max Act: 10.7757. Min Act: -0.1700
Data Index: 3109179 (Open Web Text)
Max Activating Token Index: 946
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 11.9632. Min Range: -11.9632
Max Act: 10.7757. Min Act: -0.1700
Data Index: 5868592 (Open Web Text)
Max Activating Token Index: 504
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 11.9632. Min Range: -11.9632
Max Act: 10.7132. Min Act: -0.1700
Data Index: 6860475 (Open Web Text)
Max Activating Token Index: 930
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 11.9632. Min Range: -11.9632
Max Act: 10.7132. Min Act: -0.1700
Data Index: 990132 (Open Web Text)
Max Activating Token Index: 911
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 11.9632. Min Range: -11.9632
Max Act: 10.7132. Min Act: -0.1700
Data Index: 3974894 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 11.9632. Min Range: -11.9632
Max Act: 10.7132. Min Act: -0.1700
Data Index: 5100793 (Open Web Text)
Max Activating Token Index: 382
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 11.9632. Min Range: -11.9632
Max Act: 10.7132. Min Act: -0.1700
Data Index: 4807503 (Open Web Text)
Max Activating Token Index: 449
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 11.9632. Min Range: -11.9632
Max Act: 10.7132. Min Act: -0.1700
Data Index: 7569079 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 11.9632. Min Range: -11.9632
Max Act: 10.7132. Min Act: -0.1700
Data Index: 2207959 (Open Web Text)
Max Activating Token Index: 264
Click toggle to see full text
Truncated
Full Text #19