Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2017 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.8519. Min Range: -4.8519
Max Act: 4.8519. Min Act: -0.1700
Data Index: 3356914 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.8519. Min Range: -4.8519
Max Act: 4.5082. Min Act: -0.1700
Data Index: 8443011 (Open Web Text)
Max Activating Token Index: 818
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.8519. Min Range: -4.8519
Max Act: 4.4144. Min Act: -0.1700
Data Index: 3940822 (Open Web Text)
Max Activating Token Index: 43
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.8519. Min Range: -4.8519
Max Act: 4.4144. Min Act: -0.1700
Data Index: 6014902 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.8519. Min Range: -4.8519
Max Act: 4.3519. Min Act: -0.1700
Data Index: 8170043 (Open Web Text)
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.8519. Min Range: -4.8519
Max Act: 4.3519. Min Act: -0.1700
Data Index: 2667838 (Open Web Text)
Max Activating Token Index: 1022
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.8519. Min Range: -4.8519
Max Act: 4.3207. Min Act: -0.1700
Data Index: 5780043 (Open Web Text)
Max Activating Token Index: 371
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.8519. Min Range: -4.8519
Max Act: 4.3207. Min Act: -0.1700
Data Index: 7933269 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.8519. Min Range: -4.8519
Max Act: 4.2894. Min Act: -0.1700
Data Index: 231882 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.8519. Min Range: -4.8519
Max Act: 4.3519. Min Act: -0.1700
Data Index: 7254565 (Open Web Text)
Max Activating Token Index: 781
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.8519. Min Range: -4.8519
Max Act: 4.2894. Min Act: -0.1700
Data Index: 8757277 (Open Web Text)
Max Activating Token Index: 814
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.8519. Min Range: -4.8519
Max Act: 4.2894. Min Act: -0.1700
Data Index: 554984 (Open Web Text)
Max Activating Token Index: 400
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.8519. Min Range: -4.8519
Max Act: 4.2582. Min Act: -0.1700
Data Index: 625422 (Open Web Text)
Max Activating Token Index: 74
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.8519. Min Range: -4.8519
Max Act: 4.2582. Min Act: -0.1700
Data Index: 1418620 (Open Web Text)
Max Activating Token Index: 409
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.8519. Min Range: -4.8519
Max Act: 4.1957. Min Act: -0.1700
Data Index: 6392551 (Open Web Text)
Max Activating Token Index: 736
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.8519. Min Range: -4.8519
Max Act: 4.2269. Min Act: -0.1700
Data Index: 4100324 (Open Web Text)
Max Activating Token Index: 95
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.8519. Min Range: -4.8519
Max Act: 4.1644. Min Act: -0.1700
Data Index: 1177246 (Open Web Text)
Max Activating Token Index: 868
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.8519. Min Range: -4.8519
Max Act: 4.1957. Min Act: -0.1700
Data Index: 5656365 (Open Web Text)
Max Activating Token Index: 83
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.8519. Min Range: -4.8519
Max Act: 4.1957. Min Act: -0.1700
Data Index: 6641158 (Open Web Text)
Max Activating Token Index: 94
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.8519. Min Range: -4.8519
Max Act: 4.1644. Min Act: -0.1700
Data Index: 2026300 (Open Web Text)
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #19