Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 21 in Layer 17
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.6936. Min Range: -4.6936
Max Act: 4.6936. Min Act: -0.1700
Data Index: 4466368 (Open Web Text)
Max Activating Token Index: 407
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.6936. Min Range: -4.6936
Max Act: 4.6623. Min Act: -0.1700
Data Index: 6011381 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.6936. Min Range: -4.6936
Max Act: 4.5373. Min Act: -0.1700
Data Index: 826076 (Open Web Text)
Max Activating Token Index: 549
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.6936. Min Range: -4.6936
Max Act: 4.5373. Min Act: -0.1700
Data Index: 4544550 (Open Web Text)
Max Activating Token Index: 322
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.6936. Min Range: -4.6936
Max Act: 4.5373. Min Act: -0.1700
Data Index: 1643912 (Open Web Text)
Max Activating Token Index: 902
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.6936. Min Range: -4.6936
Max Act: 4.5686. Min Act: -0.1700
Data Index: 1266998 (Open Web Text)
Max Activating Token Index: 158
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.6936. Min Range: -4.6936
Max Act: 4.5061. Min Act: -0.1700
Data Index: 7419470 (Open Web Text)
Max Activating Token Index: 287
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.6936. Min Range: -4.6936
Max Act: 4.5061. Min Act: -0.1700
Data Index: 3376491 (Open Web Text)
Max Activating Token Index: 898
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.6936. Min Range: -4.6936
Max Act: 4.5061. Min Act: -0.1700
Data Index: 3282652 (Open Web Text)
Max Activating Token Index: 898
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.6936. Min Range: -4.6936
Max Act: 4.4748. Min Act: -0.1700
Data Index: 5206156 (Open Web Text)
Max Activating Token Index: 687
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.6936. Min Range: -4.6936
Max Act: 4.4436. Min Act: -0.1700
Data Index: 8099425 (Open Web Text)
Max Activating Token Index: 137
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.6936. Min Range: -4.6936
Max Act: 4.4436. Min Act: -0.1700
Data Index: 8742996 (Open Web Text)
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.6936. Min Range: -4.6936
Max Act: 4.4123. Min Act: -0.1700
Data Index: 5084706 (Open Web Text)
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.6936. Min Range: -4.6936
Max Act: 4.4123. Min Act: -0.1700
Data Index: 5198075 (Open Web Text)
Max Activating Token Index: 264
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.6936. Min Range: -4.6936
Max Act: 4.4123. Min Act: -0.1700
Data Index: 1858920 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.6936. Min Range: -4.6936
Max Act: 4.4123. Min Act: -0.1700
Data Index: 5374136 (Open Web Text)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.6936. Min Range: -4.6936
Max Act: 4.4123. Min Act: -0.1700
Data Index: 2851756 (Open Web Text)
Max Activating Token Index: 931
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.6936. Min Range: -4.6936
Max Act: 4.3811. Min Act: -0.1700
Data Index: 5896564 (Open Web Text)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.6936. Min Range: -4.6936
Max Act: 4.3811. Min Act: -0.1700
Data Index: 6273597 (Open Web Text)
Max Activating Token Index: 104
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.6936. Min Range: -4.6936
Max Act: 4.3498. Min Act: -0.1700
Data Index: 4743355 (Open Web Text)
Max Activating Token Index: 585
Click toggle to see full text
Truncated
Full Text #19