Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2940 in Layer 16
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.4704. Min Range: -5.4704
Max Act: 5.4704. Min Act: -0.1700
Data Index: 7327890 (Open Web Text)
Max Activating Token Index: 331
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.4704. Min Range: -5.4704
Max Act: 5.3454. Min Act: -0.1700
Data Index: 507984 (Open Web Text)
Max Activating Token Index: 806
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.4704. Min Range: -5.4704
Max Act: 5.2829. Min Act: -0.1700
Data Index: 1926389 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.4704. Min Range: -5.4704
Max Act: 5.3142. Min Act: -0.1700
Data Index: 6361088 (Open Web Text)
Max Activating Token Index: 556
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.4704. Min Range: -5.4704
Max Act: 5.2517. Min Act: -0.1700
Data Index: 423733 (Open Web Text)
Max Activating Token Index: 480
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.4704. Min Range: -5.4704
Max Act: 5.2829. Min Act: -0.1700
Data Index: 7884853 (Open Web Text)
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.4704. Min Range: -5.4704
Max Act: 5.2517. Min Act: -0.1700
Data Index: 3112705 (Open Web Text)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.4704. Min Range: -5.4704
Max Act: 5.2517. Min Act: -0.1700
Data Index: 2811034 (Open Web Text)
Max Activating Token Index: 306
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.4704. Min Range: -5.4704
Max Act: 5.2517. Min Act: -0.1700
Data Index: 6555376 (Open Web Text)
Max Activating Token Index: 901
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.4704. Min Range: -5.4704
Max Act: 5.2517. Min Act: -0.1700
Data Index: 7605443 (Open Web Text)
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.4704. Min Range: -5.4704
Max Act: 5.2204. Min Act: -0.1700
Data Index: 3839627 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.4704. Min Range: -5.4704
Max Act: 5.2204. Min Act: -0.1700
Data Index: 117517 (Open Web Text)
Max Activating Token Index: 745
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.4704. Min Range: -5.4704
Max Act: 5.1892. Min Act: -0.1700
Data Index: 3694006 (Open Web Text)
Max Activating Token Index: 898
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.4704. Min Range: -5.4704
Max Act: 5.2204. Min Act: -0.1700
Data Index: 7406130 (Open Web Text)
Max Activating Token Index: 483
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.4704. Min Range: -5.4704
Max Act: 5.1892. Min Act: -0.1700
Data Index: 4510489 (Open Web Text)
Max Activating Token Index: 551
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.4704. Min Range: -5.4704
Max Act: 5.1579. Min Act: -0.1700
Data Index: 4047495 (Open Web Text)
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.4704. Min Range: -5.4704
Max Act: 5.1579. Min Act: -0.1700
Data Index: 3217786 (Open Web Text)
Max Activating Token Index: 556
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.4704. Min Range: -5.4704
Max Act: 5.1267. Min Act: -0.1700
Data Index: 1400551 (Open Web Text)
Max Activating Token Index: 745
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.4704. Min Range: -5.4704
Max Act: 5.0954. Min Act: -0.1700
Data Index: 1216553 (Open Web Text)
Max Activating Token Index: 952
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.4704. Min Range: -5.4704
Max Act: 5.1267. Min Act: -0.1700
Data Index: 2247334 (Open Web Text)
Max Activating Token Index: 497
Click toggle to see full text
Truncated
Full Text #19