Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3891 in Layer 28
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 7.7568. Min Range: -7.7568
Max Act: 7.7568. Min Act: -0.1700
Data Index: 5169145 (Open Web Text)
Max Activating Token Index: 878
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.7568. Min Range: -7.7568
Max Act: 7.5693. Min Act: -0.1700
Data Index: 1360824 (Open Web Text)
Max Activating Token Index: 765
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.7568. Min Range: -7.7568
Max Act: 7.5381. Min Act: -0.1700
Data Index: 7359521 (Open Web Text)
Max Activating Token Index: 873
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.7568. Min Range: -7.7568
Max Act: 7.4756. Min Act: -0.1700
Data Index: 5869362 (Open Web Text)
Max Activating Token Index: 1000
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.7568. Min Range: -7.7568
Max Act: 7.4443. Min Act: -0.1700
Data Index: 5709399 (Open Web Text)
Max Activating Token Index: 788
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.7568. Min Range: -7.7568
Max Act: 7.4443. Min Act: -0.1700
Data Index: 2991700 (Open Web Text)
Max Activating Token Index: 747
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.7568. Min Range: -7.7568
Max Act: 7.4131. Min Act: -0.1700
Data Index: 6353546 (Open Web Text)
Max Activating Token Index: 401
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.7568. Min Range: -7.7568
Max Act: 7.3818. Min Act: -0.1700
Data Index: 952868 (Open Web Text)
Max Activating Token Index: 304
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.7568. Min Range: -7.7568
Max Act: 7.3506. Min Act: -0.1700
Data Index: 6534418 (Open Web Text)
Max Activating Token Index: 645
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.7568. Min Range: -7.7568
Max Act: 7.3193. Min Act: -0.1700
Data Index: 2696253 (Open Web Text)
Max Activating Token Index: 566
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.7568. Min Range: -7.7568
Max Act: 7.3193. Min Act: -0.1700
Data Index: 1082835 (Open Web Text)
Max Activating Token Index: 408
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.7568. Min Range: -7.7568
Max Act: 7.3193. Min Act: -0.1700
Data Index: 8019793 (Open Web Text)
Max Activating Token Index: 154
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.7568. Min Range: -7.7568
Max Act: 7.3193. Min Act: -0.1700
Data Index: 7923761 (Open Web Text)
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.7568. Min Range: -7.7568
Max Act: 7.3193. Min Act: -0.1700
Data Index: 843099 (Open Web Text)
Max Activating Token Index: 726
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.7568. Min Range: -7.7568
Max Act: 7.2881. Min Act: -0.1700
Data Index: 2979641 (Open Web Text)
Max Activating Token Index: 878
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.7568. Min Range: -7.7568
Max Act: 7.2568. Min Act: -0.1700
Data Index: 6588998 (Open Web Text)
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.7568. Min Range: -7.7568
Max Act: 7.2256. Min Act: -0.1700
Data Index: 6303579 (Open Web Text)
Max Activating Token Index: 224
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.7568. Min Range: -7.7568
Max Act: 7.2568. Min Act: -0.1700
Data Index: 6017430 (Open Web Text)
Max Activating Token Index: 654
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.7568. Min Range: -7.7568
Max Act: 7.2256. Min Act: -0.1700
Data Index: 6214214 (Open Web Text)
Max Activating Token Index: 139
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.7568. Min Range: -7.7568
Max Act: 7.1943. Min Act: -0.1700
Data Index: 7851337 (Open Web Text)
Max Activating Token Index: 438
Click toggle to see full text
Truncated
Full Text #19