Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3953 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.8204. Min Range: -4.8204
Max Act: 4.8204. Min Act: -0.1700
Data Index: 140429 (Open Web Text)
Max Activating Token Index: 451
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.8204. Min Range: -4.8204
Max Act: 4.7267. Min Act: -0.1700
Data Index: 3120653 (Open Web Text)
Max Activating Token Index: 127
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.8204. Min Range: -4.8204
Max Act: 4.7579. Min Act: -0.1700
Data Index: 7401972 (Open Web Text)
Max Activating Token Index: 248
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.8204. Min Range: -4.8204
Max Act: 4.6017. Min Act: -0.1700
Data Index: 7574350 (Open Web Text)
Max Activating Token Index: 615
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.8204. Min Range: -4.8204
Max Act: 4.6017. Min Act: -0.1700
Data Index: 7454530 (Open Web Text)
Max Activating Token Index: 756
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.8204. Min Range: -4.8204
Max Act: 4.6017. Min Act: -0.1700
Data Index: 453927 (Open Web Text)
Max Activating Token Index: 782
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.8204. Min Range: -4.8204
Max Act: 4.5704. Min Act: -0.1700
Data Index: 180811 (Open Web Text)
Max Activating Token Index: 883
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.8204. Min Range: -4.8204
Max Act: 4.5704. Min Act: -0.1700
Data Index: 7574349 (Open Web Text)
Max Activating Token Index: 211
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.8204. Min Range: -4.8204
Max Act: 4.5392. Min Act: -0.1700
Data Index: 1977360 (Open Web Text)
Max Activating Token Index: 256
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.8204. Min Range: -4.8204
Max Act: 4.5392. Min Act: -0.1700
Data Index: 8260864 (Open Web Text)
Max Activating Token Index: 483
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.8204. Min Range: -4.8204
Max Act: 4.5079. Min Act: -0.1700
Data Index: 2665950 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.8204. Min Range: -4.8204
Max Act: 4.5392. Min Act: -0.1700
Data Index: 4995929 (Open Web Text)
Max Activating Token Index: 861
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.8204. Min Range: -4.8204
Max Act: 4.4767. Min Act: -0.1700
Data Index: 8138535 (Open Web Text)
Max Activating Token Index: 916
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.8204. Min Range: -4.8204
Max Act: 4.4454. Min Act: -0.1700
Data Index: 5708279 (Open Web Text)
Max Activating Token Index: 152
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.8204. Min Range: -4.8204
Max Act: 4.4142. Min Act: -0.1700
Data Index: 7837496 (Open Web Text)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.8204. Min Range: -4.8204
Max Act: 4.4454. Min Act: -0.1700
Data Index: 6283052 (Open Web Text)
Max Activating Token Index: 210
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.8204. Min Range: -4.8204
Max Act: 4.4454. Min Act: -0.1700
Data Index: 12565 (Open Web Text)
Max Activating Token Index: 823
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.8204. Min Range: -4.8204
Max Act: 4.3829. Min Act: -0.1700
Data Index: 8049484 (Open Web Text)
Max Activating Token Index: 202
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.8204. Min Range: -4.8204
Max Act: 4.4454. Min Act: -0.1700
Data Index: 3107212 (Open Web Text)
Max Activating Token Index: 848
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.8204. Min Range: -4.8204
Max Act: 4.4142. Min Act: -0.1700
Data Index: 4875259 (Open Web Text)
Max Activating Token Index: 175
Click toggle to see full text
Truncated
Full Text #19