Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3090 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.2884. Min Range: -5.2884
Max Act: 5.2884. Min Act: -0.1700
Data Index: 630086 (Open Web Text)
Max Activating Token Index: 46
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.2884. Min Range: -5.2884
Max Act: 5.1946. Min Act: -0.1700
Data Index: 2941644 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.2884. Min Range: -5.2884
Max Act: 5.1634. Min Act: -0.1700
Data Index: 3849320 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.2884. Min Range: -5.2884
Max Act: 5.1321. Min Act: -0.1700
Data Index: 4978508 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.2884. Min Range: -5.2884
Max Act: 5.1321. Min Act: -0.1700
Data Index: 5130064 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.2884. Min Range: -5.2884
Max Act: 5.1321. Min Act: -0.1700
Data Index: 2941638 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.2884. Min Range: -5.2884
Max Act: 5.1009. Min Act: -0.1700
Data Index: 4229989 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.2884. Min Range: -5.2884
Max Act: 5.0696. Min Act: -0.1700
Data Index: 2683631 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.2884. Min Range: -5.2884
Max Act: 5.0696. Min Act: -0.1700
Data Index: 7618205 (Open Web Text)
Max Activating Token Index: 27
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.2884. Min Range: -5.2884
Max Act: 5.0696. Min Act: -0.1700
Data Index: 972903 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.2884. Min Range: -5.2884
Max Act: 5.0696. Min Act: -0.1700
Data Index: 862166 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.2884. Min Range: -5.2884
Max Act: 5.0696. Min Act: -0.1700
Data Index: 1708440 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.2884. Min Range: -5.2884
Max Act: 5.0384. Min Act: -0.1700
Data Index: 3932678 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.2884. Min Range: -5.2884
Max Act: 5.0696. Min Act: -0.1700
Data Index: 5670512 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.2884. Min Range: -5.2884
Max Act: 5.0384. Min Act: -0.1699
Data Index: 1600531 (Open Web Text)
Max Activating Token Index: 705
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.2884. Min Range: -5.2884
Max Act: 5.0384. Min Act: -0.1700
Data Index: 6787544 (Open Web Text)
Max Activating Token Index: 37
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.2884. Min Range: -5.2884
Max Act: 5.0384. Min Act: -0.1700
Data Index: 6670998 (Open Web Text)
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.2884. Min Range: -5.2884
Max Act: 5.0384. Min Act: -0.1700
Data Index: 7721697 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.2884. Min Range: -5.2884
Max Act: 5.0384. Min Act: -0.1700
Data Index: 1477197 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.2884. Min Range: -5.2884
Max Act: 4.9759. Min Act: -0.1700
Data Index: 4317899 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #19