Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2828 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.3516. Min Range: -4.3516
Max Act: 4.3516. Min Act: -0.1700
Data Index: 5632711 (Open Web Text)
Max Activating Token Index: 776
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.3516. Min Range: -4.3516
Max Act: 4.2578. Min Act: -0.1700
Data Index: 6245584 (Open Web Text)
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.3516. Min Range: -4.3516
Max Act: 4.2266. Min Act: -0.1700
Data Index: 6961903 (Open Web Text)
Max Activating Token Index: 66
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.3516. Min Range: -4.3516
Max Act: 4.1953. Min Act: -0.1700
Data Index: 1858818 (Open Web Text)
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.3516. Min Range: -4.3516
Max Act: 4.1953. Min Act: -0.1700
Data Index: 4100974 (Open Web Text)
Max Activating Token Index: 68
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.3516. Min Range: -4.3516
Max Act: 4.1640. Min Act: -0.1700
Data Index: 2627758 (Open Web Text)
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.3516. Min Range: -4.3516
Max Act: 4.1328. Min Act: -0.1700
Data Index: 3155566 (Open Web Text)
Max Activating Token Index: 237
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.3516. Min Range: -4.3516
Max Act: 4.1953. Min Act: -0.1700
Data Index: 323429 (Open Web Text)
Max Activating Token Index: 630
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.3516. Min Range: -4.3516
Max Act: 4.1328. Min Act: -0.1700
Data Index: 8794422 (Open Web Text)
Max Activating Token Index: 890
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.3516. Min Range: -4.3516
Max Act: 4.1015. Min Act: -0.1700
Data Index: 2052216 (Open Web Text)
Max Activating Token Index: 511
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.3516. Min Range: -4.3516
Max Act: 4.1328. Min Act: -0.1700
Data Index: 1410040 (Open Web Text)
Max Activating Token Index: 551
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.3516. Min Range: -4.3516
Max Act: 4.1328. Min Act: -0.1700
Data Index: 1187539 (Open Web Text)
Max Activating Token Index: 276
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.3516. Min Range: -4.3516
Max Act: 4.1015. Min Act: -0.1700
Data Index: 2589664 (Open Web Text)
Max Activating Token Index: 443
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.3516. Min Range: -4.3516
Max Act: 4.1328. Min Act: -0.1700
Data Index: 137362 (Open Web Text)
Max Activating Token Index: 42
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.3516. Min Range: -4.3516
Max Act: 4.1640. Min Act: -0.1700
Data Index: 3983504 (Open Web Text)
Max Activating Token Index: 608
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.3516. Min Range: -4.3516
Max Act: 4.1328. Min Act: -0.1700
Data Index: 607064 (Open Web Text)
Max Activating Token Index: 77
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.3516. Min Range: -4.3516
Max Act: 4.1328. Min Act: -0.1700
Data Index: 2990509 (Open Web Text)
Max Activating Token Index: 87
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.3516. Min Range: -4.3516
Max Act: 4.1015. Min Act: -0.1700
Data Index: 3983503 (Open Web Text)
Max Activating Token Index: 724
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.3516. Min Range: -4.3516
Max Act: 4.0703. Min Act: -0.1700
Data Index: 5108242 (Open Web Text)
Max Activating Token Index: 112
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.3516. Min Range: -4.3516
Max Act: 4.1015. Min Act: -0.1700
Data Index: 1585232 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #19