Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2592 in Layer 17
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 6.1473. Min Range: -6.1473
Max Act: 6.1473. Min Act: -0.1700
Data Index: 3183637 (Open Web Text)
Max Activating Token Index: 276
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.1473. Min Range: -6.1473
Max Act: 5.9910. Min Act: -0.1700
Data Index: 1100086 (Open Web Text)
Max Activating Token Index: 139
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.1473. Min Range: -6.1473
Max Act: 5.9910. Min Act: -0.1700
Data Index: 6461945 (Open Web Text)
Max Activating Token Index: 91
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.1473. Min Range: -6.1473
Max Act: 5.9598. Min Act: -0.1700
Data Index: 3381200 (Open Web Text)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.1473. Min Range: -6.1473
Max Act: 5.9598. Min Act: -0.1700
Data Index: 6065523 (Open Web Text)
Max Activating Token Index: 376
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.1473. Min Range: -6.1473
Max Act: 5.9910. Min Act: -0.1700
Data Index: 4723705 (Open Web Text)
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.1473. Min Range: -6.1473
Max Act: 5.8973. Min Act: -0.1700
Data Index: 2175471 (Open Web Text)
Max Activating Token Index: 668
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.1473. Min Range: -6.1473
Max Act: 5.8660. Min Act: -0.1700
Data Index: 3998559 (Open Web Text)
Max Activating Token Index: 54
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.1473. Min Range: -6.1473
Max Act: 5.8660. Min Act: -0.1700
Data Index: 2213144 (Open Web Text)
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.1473. Min Range: -6.1473
Max Act: 5.8660. Min Act: -0.1700
Data Index: 4524144 (Open Web Text)
Max Activating Token Index: 179
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.1473. Min Range: -6.1473
Max Act: 5.8348. Min Act: -0.1700
Data Index: 1410629 (Open Web Text)
Max Activating Token Index: 326
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.1473. Min Range: -6.1473
Max Act: 5.8348. Min Act: -0.1700
Data Index: 1626513 (Open Web Text)
Max Activating Token Index: 438
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.1473. Min Range: -6.1473
Max Act: 5.8348. Min Act: -0.1700
Data Index: 3971502 (Open Web Text)
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.1473. Min Range: -6.1473
Max Act: 5.8348. Min Act: -0.1700
Data Index: 4872818 (Open Web Text)
Max Activating Token Index: 685
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.1473. Min Range: -6.1473
Max Act: 5.8035. Min Act: -0.1700
Data Index: 6449097 (Open Web Text)
Max Activating Token Index: 256
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.1473. Min Range: -6.1473
Max Act: 5.8035. Min Act: -0.1700
Data Index: 4915365 (Open Web Text)
Max Activating Token Index: 586
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.1473. Min Range: -6.1473
Max Act: 5.7723. Min Act: -0.1700
Data Index: 8033016 (Open Web Text)
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.1473. Min Range: -6.1473
Max Act: 5.7723. Min Act: -0.1700
Data Index: 1673796 (Open Web Text)
Max Activating Token Index: 194
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.1473. Min Range: -6.1473
Max Act: 5.7410. Min Act: -0.1700
Data Index: 4529357 (Open Web Text)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.1473. Min Range: -6.1473
Max Act: 5.7098. Min Act: -0.1700
Data Index: 2670084 (Open Web Text)
Max Activating Token Index: 186
Click toggle to see full text
Truncated
Full Text #19