Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 20 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.8539. Min Range: -4.8539
Max Act: 4.8539. Min Act: -0.1700
Data Index: 8709463 (Open Web Text)
Max Activating Token Index: 646
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.8539. Min Range: -4.8539
Max Act: 4.8227. Min Act: -0.1700
Data Index: 2890808 (Open Web Text)
Max Activating Token Index: 154
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.8539. Min Range: -4.8539
Max Act: 4.7602. Min Act: -0.1700
Data Index: 157138 (Open Web Text)
Max Activating Token Index: 900
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.8539. Min Range: -4.8539
Max Act: 4.7602. Min Act: -0.1700
Data Index: 2928811 (Open Web Text)
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.8539. Min Range: -4.8539
Max Act: 4.7914. Min Act: -0.1700
Data Index: 8061149 (Open Web Text)
Max Activating Token Index: 1022
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.8539. Min Range: -4.8539
Max Act: 4.7914. Min Act: -0.1700
Data Index: 7139701 (Open Web Text)
Max Activating Token Index: 272
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.8539. Min Range: -4.8539
Max Act: 4.7914. Min Act: -0.1700
Data Index: 8162345 (Open Web Text)
Max Activating Token Index: 766
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.8539. Min Range: -4.8539
Max Act: 4.7602. Min Act: -0.1700
Data Index: 6007360 (Open Web Text)
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.8539. Min Range: -4.8539
Max Act: 4.6977. Min Act: -0.1700
Data Index: 338074 (Open Web Text)
Max Activating Token Index: 241
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.8539. Min Range: -4.8539
Max Act: 4.7289. Min Act: -0.1700
Data Index: 5410475 (Open Web Text)
Max Activating Token Index: 235
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.8539. Min Range: -4.8539
Max Act: 4.7289. Min Act: -0.1700
Data Index: 5445363 (Open Web Text)
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.8539. Min Range: -4.8539
Max Act: 4.7289. Min Act: -0.1700
Data Index: 7353976 (Open Web Text)
Max Activating Token Index: 789
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.8539. Min Range: -4.8539
Max Act: 4.6977. Min Act: -0.1700
Data Index: 5320422 (Open Web Text)
Max Activating Token Index: 252
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.8539. Min Range: -4.8539
Max Act: 4.6977. Min Act: -0.1700
Data Index: 7267743 (Open Web Text)
Max Activating Token Index: 254
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.8539. Min Range: -4.8539
Max Act: 4.6977. Min Act: -0.1700
Data Index: 7091026 (Open Web Text)
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.8539. Min Range: -4.8539
Max Act: 4.7289. Min Act: -0.1700
Data Index: 737020 (Open Web Text)
Max Activating Token Index: 668
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.8539. Min Range: -4.8539
Max Act: 4.6664. Min Act: -0.1700
Data Index: 8572062 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.8539. Min Range: -4.8539
Max Act: 4.6664. Min Act: -0.1700
Data Index: 4142008 (Open Web Text)
Max Activating Token Index: 70
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.8539. Min Range: -4.8539
Max Act: 4.6664. Min Act: -0.1700
Data Index: 5906056 (Open Web Text)
Max Activating Token Index: 122
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.8539. Min Range: -4.8539
Max Act: 4.6664. Min Act: -0.1700
Data Index: 965496 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #19