Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1775 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.5257. Min Range: -7.5257
Max Act: 7.5257. Min Act: -0.1700
Data Index: 8509754 (Open Web Text)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.5257. Min Range: -7.5257
Max Act: 7.2757. Min Act: -0.1700
Data Index: 75932 (Open Web Text)
Max Activating Token Index: 291
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.5257. Min Range: -7.5257
Max Act: 7.2132. Min Act: -0.1700
Data Index: 759110 (Open Web Text)
Max Activating Token Index: 1016
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.5257. Min Range: -7.5257
Max Act: 7.1195. Min Act: -0.1700
Data Index: 2301839 (Open Web Text)
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.5257. Min Range: -7.5257
Max Act: 7.0882. Min Act: -0.1700
Data Index: 2565484 (Open Web Text)
Max Activating Token Index: 487
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.5257. Min Range: -7.5257
Max Act: 7.0570. Min Act: -0.1700
Data Index: 2763881 (Open Web Text)
Max Activating Token Index: 677
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.5257. Min Range: -7.5257
Max Act: 7.0257. Min Act: -0.1700
Data Index: 5754036 (Open Web Text)
Max Activating Token Index: 337
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.5257. Min Range: -7.5257
Max Act: 7.0257. Min Act: -0.1700
Data Index: 7296154 (Open Web Text)
Max Activating Token Index: 530
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.5257. Min Range: -7.5257
Max Act: 6.9945. Min Act: -0.1700
Data Index: 4203714 (Open Web Text)
Max Activating Token Index: 724
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.5257. Min Range: -7.5257
Max Act: 6.9945. Min Act: -0.1700
Data Index: 1283091 (Open Web Text)
Max Activating Token Index: 730
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.5257. Min Range: -7.5257
Max Act: 6.9945. Min Act: -0.1700
Data Index: 4066269 (Open Web Text)
Max Activating Token Index: 934
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.5257. Min Range: -7.5257
Max Act: 6.9945. Min Act: -0.1700
Data Index: 6864542 (Open Web Text)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.5257. Min Range: -7.5257
Max Act: 6.9945. Min Act: -0.1700
Data Index: 2355748 (Open Web Text)
Max Activating Token Index: 626
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.5257. Min Range: -7.5257
Max Act: 6.9945. Min Act: -0.1700
Data Index: 5950765 (Open Web Text)
Max Activating Token Index: 438
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.5257. Min Range: -7.5257
Max Act: 6.9632. Min Act: -0.1700
Data Index: 5408025 (Open Web Text)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.5257. Min Range: -7.5257
Max Act: 6.9632. Min Act: -0.1700
Data Index: 5974068 (Open Web Text)
Max Activating Token Index: 805
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.5257. Min Range: -7.5257
Max Act: 6.9632. Min Act: -0.1700
Data Index: 4822282 (Open Web Text)
Max Activating Token Index: 211
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.5257. Min Range: -7.5257
Max Act: 6.9632. Min Act: -0.1700
Data Index: 2310120 (Open Web Text)
Max Activating Token Index: 852
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.5257. Min Range: -7.5257
Max Act: 6.9320. Min Act: -0.1700
Data Index: 7671751 (Open Web Text)
Max Activating Token Index: 732
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.5257. Min Range: -7.5257
Max Act: 6.9320. Min Act: -0.1700
Data Index: 7716687 (Open Web Text)
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #19