Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3734 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 1.5950. Min Range: -1.5950
Max Act: 1.5950. Min Act: -0.1700
Data Index: 5793737 (Open Web Text)
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.5950. Min Range: -1.5950
Max Act: 1.4899. Min Act: -0.1700
Data Index: 5725368 (Open Web Text)
Max Activating Token Index: 51
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.5950. Min Range: -1.5950
Max Act: 1.4371. Min Act: -0.1700
Data Index: 3109860 (Open Web Text)
Max Activating Token Index: 48
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.5950. Min Range: -1.5950
Max Act: 1.3578. Min Act: -0.1700
Data Index: 2168848 (Open Web Text)
Max Activating Token Index: 43
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.5950. Min Range: -1.5950
Max Act: 1.3490. Min Act: -0.1700
Data Index: 1060376 (Open Web Text)
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.5950. Min Range: -1.5950
Max Act: 1.3490. Min Act: -0.1700
Data Index: 7285664 (Open Web Text)
Max Activating Token Index: 63
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.5950. Min Range: -1.5950
Max Act: 1.3402. Min Act: -0.1700
Data Index: 431123 (Open Web Text)
Max Activating Token Index: 40
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.5950. Min Range: -1.5950
Max Act: 1.3402. Min Act: -0.1700
Data Index: 777754 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.5950. Min Range: -1.5950
Max Act: 1.3314. Min Act: -0.1700
Data Index: 3257705 (Open Web Text)
Max Activating Token Index: 50
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.5950. Min Range: -1.5950
Max Act: 1.3225. Min Act: -0.1700
Data Index: 1292401 (Open Web Text)
Max Activating Token Index: 49
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.5950. Min Range: -1.5950
Max Act: 1.3225. Min Act: -0.1700
Data Index: 918151 (Open Web Text)
Max Activating Token Index: 20
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.5950. Min Range: -1.5950
Max Act: 1.2961. Min Act: -0.1700
Data Index: 2357873 (Open Web Text)
Max Activating Token Index: 44
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.5950. Min Range: -1.5950
Max Act: 1.2961. Min Act: -0.1700
Data Index: 7929069 (Open Web Text)
Max Activating Token Index: 70
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.5950. Min Range: -1.5950
Max Act: 1.3049. Min Act: -0.1700
Data Index: 4068428 (Open Web Text)
Max Activating Token Index: 43
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.5950. Min Range: -1.5950
Max Act: 1.2961. Min Act: -0.1700
Data Index: 6529974 (Open Web Text)
Max Activating Token Index: 46
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.5950. Min Range: -1.5950
Max Act: 1.2961. Min Act: -0.1700
Data Index: 2757636 (Open Web Text)
Max Activating Token Index: 25
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.5950. Min Range: -1.5950
Max Act: 1.2873. Min Act: -0.1700
Data Index: 2501732 (Open Web Text)
Max Activating Token Index: 30
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.5950. Min Range: -1.5950
Max Act: 1.2696. Min Act: -0.1700
Data Index: 4202408 (Open Web Text)
Max Activating Token Index: 36
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.5950. Min Range: -1.5950
Max Act: 1.2696. Min Act: -0.1700
Data Index: 8401502 (Open Web Text)
Max Activating Token Index: 20
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.5950. Min Range: -1.5950
Max Act: 1.2608. Min Act: -0.1700
Data Index: 146212 (Open Web Text)
Max Activating Token Index: 123
Click toggle to see full text
Truncated
Full Text #19