Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2939 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.0764. Min Range: -3.0764
Max Act: 3.0764. Min Act: -0.1700
Data Index: 4509078 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.0764. Min Range: -3.0764
Max Act: 3.0606. Min Act: -0.1700
Data Index: 7376350 (Open Web Text)
Max Activating Token Index: 20
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.0764. Min Range: -3.0764
Max Act: 3.0764. Min Act: -0.1700
Data Index: 2219237 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.0764. Min Range: -3.0764
Max Act: 2.9816. Min Act: -0.1700
Data Index: 7803792 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.0764. Min Range: -3.0764
Max Act: 2.9183. Min Act: -0.1700
Data Index: 478574 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.0764. Min Range: -3.0764
Max Act: 2.8707. Min Act: -0.1700
Data Index: 2647874 (Open Web Text)
Max Activating Token Index: 176
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.0764. Min Range: -3.0764
Max Act: 2.8707. Min Act: -0.1700
Data Index: 6304405 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.0764. Min Range: -3.0764
Max Act: 2.8707. Min Act: -0.1700
Data Index: 5053980 (Open Web Text)
Max Activating Token Index: 30
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.0764. Min Range: -3.0764
Max Act: 2.8549. Min Act: -0.1700
Data Index: 4517672 (Open Web Text)
Max Activating Token Index: 45
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.0764. Min Range: -3.0764
Max Act: 2.8390. Min Act: -0.1700
Data Index: 4893592 (Open Web Text)
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.0764. Min Range: -3.0764
Max Act: 2.8231. Min Act: -0.1700
Data Index: 4705526 (Open Web Text)
Max Activating Token Index: 52
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.0764. Min Range: -3.0764
Max Act: 2.8231. Min Act: -0.1700
Data Index: 8444990 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.0764. Min Range: -3.0764
Max Act: 2.8231. Min Act: -0.1700
Data Index: 2202018 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.0764. Min Range: -3.0764
Max Act: 2.8231. Min Act: -0.1700
Data Index: 4833856 (Open Web Text)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.0764. Min Range: -3.0764
Max Act: 2.8072. Min Act: -0.1700
Data Index: 3093474 (Open Web Text)
Max Activating Token Index: 237
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.0764. Min Range: -3.0764
Max Act: 2.8072. Min Act: -0.1700
Data Index: 2295087 (Open Web Text)
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.0764. Min Range: -3.0764
Max Act: 2.8072. Min Act: -0.1700
Data Index: 7549051 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.0764. Min Range: -3.0764
Max Act: 2.8072. Min Act: -0.1700
Data Index: 7447883 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.0764. Min Range: -3.0764
Max Act: 2.8072. Min Act: -0.1700
Data Index: 6549783 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.0764. Min Range: -3.0764
Max Act: 2.7912. Min Act: -0.1700
Data Index: 6255067 (Open Web Text)
Max Activating Token Index: 112
Click toggle to see full text
Truncated
Full Text #19