Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 273 in Layer 6
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.3608. Min Range: -4.3608
Max Act: 4.3608. Min Act: -0.1700
Data Index: 3708774 (Open Web Text)
Max Activating Token Index: 253
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.3608. Min Range: -4.3608
Max Act: 4.2983. Min Act: -0.1700
Data Index: 6992000 (Open Web Text)
Max Activating Token Index: 919
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.3608. Min Range: -4.3608
Max Act: 4.3295. Min Act: -0.1700
Data Index: 2591926 (Open Web Text)
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.3608. Min Range: -4.3608
Max Act: 4.3295. Min Act: -0.1700
Data Index: 1459728 (Open Web Text)
Max Activating Token Index: 168
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.3608. Min Range: -4.3608
Max Act: 4.3295. Min Act: -0.1700
Data Index: 241212 (Open Web Text)
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.3608. Min Range: -4.3608
Max Act: 4.3295. Min Act: -0.1700
Data Index: 7218213 (Open Web Text)
Max Activating Token Index: 78
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.3608. Min Range: -4.3608
Max Act: 4.2358. Min Act: -0.1700
Data Index: 471830 (Open Web Text)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.3608. Min Range: -4.3608
Max Act: 4.2670. Min Act: -0.1700
Data Index: 6243251 (Open Web Text)
Max Activating Token Index: 939
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.3608. Min Range: -4.3608
Max Act: 4.2670. Min Act: -0.1700
Data Index: 5233226 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.3608. Min Range: -4.3608
Max Act: 4.2670. Min Act: -0.1700
Data Index: 3562155 (Open Web Text)
Max Activating Token Index: 890
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.3608. Min Range: -4.3608
Max Act: 4.2358. Min Act: -0.1700
Data Index: 5615690 (Open Web Text)
Max Activating Token Index: 146
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.3608. Min Range: -4.3608
Max Act: 4.2358. Min Act: -0.1700
Data Index: 6816531 (Open Web Text)
Max Activating Token Index: 363
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.3608. Min Range: -4.3608
Max Act: 4.2358. Min Act: -0.1700
Data Index: 6184030 (Open Web Text)
Max Activating Token Index: 36
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.3608. Min Range: -4.3608
Max Act: 4.2358. Min Act: -0.1700
Data Index: 7933990 (Open Web Text)
Max Activating Token Index: 213
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.3608. Min Range: -4.3608
Max Act: 4.2358. Min Act: -0.1700
Data Index: 4868291 (Open Web Text)
Max Activating Token Index: 908
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.3608. Min Range: -4.3608
Max Act: 4.2358. Min Act: -0.1700
Data Index: 2533197 (Open Web Text)
Max Activating Token Index: 893
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.3608. Min Range: -4.3608
Max Act: 4.2045. Min Act: -0.1700
Data Index: 1397689 (Open Web Text)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.3608. Min Range: -4.3608
Max Act: 4.1732. Min Act: -0.1700
Data Index: 3127920 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.3608. Min Range: -4.3608
Max Act: 4.2045. Min Act: -0.1700
Data Index: 4869649 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.3608. Min Range: -4.3608
Max Act: 4.2358. Min Act: -0.1700
Data Index: 4254850 (Open Web Text)
Max Activating Token Index: 820
Click toggle to see full text
Truncated
Full Text #19