Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1354 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.0816. Min Range: -5.0816
Max Act: 5.0816. Min Act: -0.1700
Data Index: 860519 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0816. Min Range: -5.0816
Max Act: 5.0816. Min Act: -0.1700
Data Index: 245208 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0816. Min Range: -5.0816
Max Act: 5.0503. Min Act: -0.1700
Data Index: 6545273 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0816. Min Range: -5.0816
Max Act: 5.0503. Min Act: -0.1700
Data Index: 5048903 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0816. Min Range: -5.0816
Max Act: 5.0503. Min Act: -0.1700
Data Index: 5048878 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0816. Min Range: -5.0816
Max Act: 5.0503. Min Act: -0.1700
Data Index: 5048872 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0816. Min Range: -5.0816
Max Act: 5.0191. Min Act: -0.1700
Data Index: 111206 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0816. Min Range: -5.0816
Max Act: 4.9878. Min Act: -0.1700
Data Index: 8232490 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0816. Min Range: -5.0816
Max Act: 4.9878. Min Act: -0.1700
Data Index: 1159252 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0816. Min Range: -5.0816
Max Act: 4.9878. Min Act: -0.1700
Data Index: 5093243 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0816. Min Range: -5.0816
Max Act: 4.9878. Min Act: -0.1700
Data Index: 3922711 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0816. Min Range: -5.0816
Max Act: 4.9878. Min Act: -0.1700
Data Index: 7700773 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0816. Min Range: -5.0816
Max Act: 4.9878. Min Act: -0.1700
Data Index: 630599 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0816. Min Range: -5.0816
Max Act: 4.9878. Min Act: -0.1700
Data Index: 6176496 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0816. Min Range: -5.0816
Max Act: 4.9566. Min Act: -0.1700
Data Index: 2707776 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0816. Min Range: -5.0816
Max Act: 4.9253. Min Act: -0.1700
Data Index: 540183 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0816. Min Range: -5.0816
Max Act: 4.9566. Min Act: -0.1700
Data Index: 5325261 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0816. Min Range: -5.0816
Max Act: 4.9566. Min Act: -0.1700
Data Index: 934877 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0816. Min Range: -5.0816
Max Act: 4.9566. Min Act: -0.1700
Data Index: 993846 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0816. Min Range: -5.0816
Max Act: 4.9566. Min Act: -0.1700
Data Index: 558720 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #19