Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4378 in Layer 37
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.8437. Min Range: -8.8437
Max Act: 8.8437. Min Act: -0.1700
Data Index: 1071236 (Open Web Text)
Max Activating Token Index: 776
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.8437. Min Range: -8.8437
Max Act: 8.7187. Min Act: -0.1700
Data Index: 1528469 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.8437. Min Range: -8.8437
Max Act: 8.7187. Min Act: -0.1700
Data Index: 732663 (Open Web Text)
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.8437. Min Range: -8.8437
Max Act: 8.5937. Min Act: -0.1700
Data Index: 1359339 (Open Web Text)
Max Activating Token Index: 1006
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.8437. Min Range: -8.8437
Max Act: 8.5312. Min Act: -0.1700
Data Index: 8023901 (Open Web Text)
Max Activating Token Index: 699
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.8437. Min Range: -8.8437
Max Act: 8.4687. Min Act: -0.1700
Data Index: 5016006 (Open Web Text)
Max Activating Token Index: 1004
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.8437. Min Range: -8.8437
Max Act: 8.4687. Min Act: -0.1700
Data Index: 3201900 (Open Web Text)
Max Activating Token Index: 80
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.8437. Min Range: -8.8437
Max Act: 8.4687. Min Act: -0.1700
Data Index: 1359340 (Open Web Text)
Max Activating Token Index: 51
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.8437. Min Range: -8.8437
Max Act: 8.4062. Min Act: -0.1700
Data Index: 4206131 (Open Web Text)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.8437. Min Range: -8.8437
Max Act: 8.4062. Min Act: -0.1700
Data Index: 5532094 (Open Web Text)
Max Activating Token Index: 660
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.8437. Min Range: -8.8437
Max Act: 8.3437. Min Act: -0.1700
Data Index: 613258 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.8437. Min Range: -8.8437
Max Act: 8.3437. Min Act: -0.1700
Data Index: 5840268 (Open Web Text)
Max Activating Token Index: 637
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.8437. Min Range: -8.8437
Max Act: 8.3437. Min Act: -0.1700
Data Index: 5587049 (Open Web Text)
Max Activating Token Index: 256
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.8437. Min Range: -8.8437
Max Act: 8.3437. Min Act: -0.1700
Data Index: 7186329 (Open Web Text)
Max Activating Token Index: 723
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.8437. Min Range: -8.8437
Max Act: 8.3437. Min Act: -0.1700
Data Index: 7179320 (Open Web Text)
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.8437. Min Range: -8.8437
Max Act: 8.3437. Min Act: -0.1700
Data Index: 4566847 (Open Web Text)
Max Activating Token Index: 929
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.8437. Min Range: -8.8437
Max Act: 8.2812. Min Act: -0.1700
Data Index: 5683964 (Open Web Text)
Max Activating Token Index: 833
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.8437. Min Range: -8.8437
Max Act: 8.2812. Min Act: -0.1700
Data Index: 6789838 (Open Web Text)
Max Activating Token Index: 693
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.8437. Min Range: -8.8437
Max Act: 8.2812. Min Act: -0.1700
Data Index: 1105621 (Open Web Text)
Max Activating Token Index: 862
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.8437. Min Range: -8.8437
Max Act: 8.2812. Min Act: -0.1700
Data Index: 1187900 (Open Web Text)
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #19