Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2362 in Layer 12
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.6388. Min Range: -4.6388
Max Act: 4.6388. Min Act: -0.1700
Data Index: 3559547 (Open Web Text)
Max Activating Token Index: 785
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.6388. Min Range: -4.6388
Max Act: 4.6075. Min Act: -0.1700
Data Index: 3851833 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.6388. Min Range: -4.6388
Max Act: 4.5763. Min Act: -0.1700
Data Index: 3708928 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.6388. Min Range: -4.6388
Max Act: 4.5763. Min Act: -0.1700
Data Index: 591860 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.6388. Min Range: -4.6388
Max Act: 4.4513. Min Act: -0.1700
Data Index: 438311 (Open Web Text)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.6388. Min Range: -4.6388
Max Act: 4.4513. Min Act: -0.1700
Data Index: 2724662 (Open Web Text)
Max Activating Token Index: 360
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.6388. Min Range: -4.6388
Max Act: 4.4200. Min Act: -0.1700
Data Index: 2702205 (Open Web Text)
Max Activating Token Index: 682
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.6388. Min Range: -4.6388
Max Act: 4.3888. Min Act: -0.1700
Data Index: 1940348 (Open Web Text)
Max Activating Token Index: 914
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.6388. Min Range: -4.6388
Max Act: 4.3575. Min Act: -0.1700
Data Index: 6824794 (Open Web Text)
Max Activating Token Index: 943
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.6388. Min Range: -4.6388
Max Act: 4.3575. Min Act: -0.1700
Data Index: 1973808 (Open Web Text)
Max Activating Token Index: 85
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.6388. Min Range: -4.6388
Max Act: 4.3575. Min Act: -0.1700
Data Index: 8115856 (Open Web Text)
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.6388. Min Range: -4.6388
Max Act: 4.3575. Min Act: -0.1700
Data Index: 6560519 (Open Web Text)
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.6388. Min Range: -4.6388
Max Act: 4.3575. Min Act: -0.1700
Data Index: 4815557 (Open Web Text)
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.6388. Min Range: -4.6388
Max Act: 4.3263. Min Act: -0.1700
Data Index: 5562156 (Open Web Text)
Max Activating Token Index: 126
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.6388. Min Range: -4.6388
Max Act: 4.3263. Min Act: -0.1700
Data Index: 5270374 (Open Web Text)
Max Activating Token Index: 184
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.6388. Min Range: -4.6388
Max Act: 4.2950. Min Act: -0.1700
Data Index: 3542351 (Open Web Text)
Max Activating Token Index: 898
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.6388. Min Range: -4.6388
Max Act: 4.2950. Min Act: -0.1700
Data Index: 5082799 (Open Web Text)
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.6388. Min Range: -4.6388
Max Act: 4.2950. Min Act: -0.1700
Data Index: 7713996 (Open Web Text)
Max Activating Token Index: 419
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.6388. Min Range: -4.6388
Max Act: 4.2950. Min Act: -0.1700
Data Index: 5414403 (Open Web Text)
Max Activating Token Index: 729
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.6388. Min Range: -4.6388
Max Act: 4.2950. Min Act: -0.1700
Data Index: 2988072 (Open Web Text)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #19