Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3464 in Layer 16
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.0230. Min Range: -5.0230
Max Act: 5.0230. Min Act: -0.1700
Data Index: 2722746 (Open Web Text)
Max Activating Token Index: 191
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0230. Min Range: -5.0230
Max Act: 4.9917. Min Act: -0.1700
Data Index: 2738018 (Open Web Text)
Max Activating Token Index: 669
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0230. Min Range: -5.0230
Max Act: 4.8980. Min Act: -0.1700
Data Index: 7374929 (Open Web Text)
Max Activating Token Index: 92
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0230. Min Range: -5.0230
Max Act: 4.8667. Min Act: -0.1700
Data Index: 4809915 (Open Web Text)
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0230. Min Range: -5.0230
Max Act: 4.8667. Min Act: -0.1700
Data Index: 7947509 (Open Web Text)
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0230. Min Range: -5.0230
Max Act: 4.8355. Min Act: -0.1700
Data Index: 7703481 (Open Web Text)
Max Activating Token Index: 233
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0230. Min Range: -5.0230
Max Act: 4.8355. Min Act: -0.1700
Data Index: 4688353 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0230. Min Range: -5.0230
Max Act: 4.8355. Min Act: -0.1700
Data Index: 292354 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0230. Min Range: -5.0230
Max Act: 4.7730. Min Act: -0.1700
Data Index: 4559196 (Open Web Text)
Max Activating Token Index: 84
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0230. Min Range: -5.0230
Max Act: 4.7417. Min Act: -0.1700
Data Index: 3844023 (Open Web Text)
Max Activating Token Index: 82
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0230. Min Range: -5.0230
Max Act: 4.7730. Min Act: -0.1700
Data Index: 8397342 (Open Web Text)
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0230. Min Range: -5.0230
Max Act: 4.7417. Min Act: -0.1700
Data Index: 6402703 (Open Web Text)
Max Activating Token Index: 955
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0230. Min Range: -5.0230
Max Act: 4.7105. Min Act: -0.1700
Data Index: 7673738 (Open Web Text)
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0230. Min Range: -5.0230
Max Act: 4.7105. Min Act: -0.1700
Data Index: 12365 (Open Web Text)
Max Activating Token Index: 621
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0230. Min Range: -5.0230
Max Act: 4.7105. Min Act: -0.1700
Data Index: 856089 (Open Web Text)
Max Activating Token Index: 900
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0230. Min Range: -5.0230
Max Act: 4.7105. Min Act: -0.1700
Data Index: 4384842 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0230. Min Range: -5.0230
Max Act: 4.6792. Min Act: -0.1700
Data Index: 3142516 (Open Web Text)
Max Activating Token Index: 636
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0230. Min Range: -5.0230
Max Act: 4.6792. Min Act: -0.1700
Data Index: 1596512 (Open Web Text)
Max Activating Token Index: 363
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0230. Min Range: -5.0230
Max Act: 4.6480. Min Act: -0.1700
Data Index: 3375076 (Open Web Text)
Max Activating Token Index: 1004
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0230. Min Range: -5.0230
Max Act: 4.6792. Min Act: -0.1700
Data Index: 3960645 (Open Web Text)
Max Activating Token Index: 317
Click toggle to see full text
Truncated
Full Text #19