Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3604 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.5886. Min Range: -3.5886
Max Act: 3.5886. Min Act: -0.1700
Data Index: 6261183 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.5886. Min Range: -3.5886
Max Act: 3.5886. Min Act: -0.1700
Data Index: 4573885 (Open Web Text)
Max Activating Token Index: 31
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.5886. Min Range: -3.5886
Max Act: 3.4947. Min Act: -0.1700
Data Index: 3225140 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.5886. Min Range: -3.5886
Max Act: 3.4634. Min Act: -0.1700
Data Index: 8124406 (Open Web Text)
Max Activating Token Index: 31
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.5886. Min Range: -3.5886
Max Act: 3.4007. Min Act: -0.1700
Data Index: 8526709 (Open Web Text)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.5886. Min Range: -3.5886
Max Act: 3.4007. Min Act: -0.1700
Data Index: 5015805 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.5886. Min Range: -3.5886
Max Act: 3.4007. Min Act: -0.1700
Data Index: 5055256 (Open Web Text)
Max Activating Token Index: 20
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.5886. Min Range: -3.5886
Max Act: 3.4007. Min Act: -0.1700
Data Index: 699166 (Open Web Text)
Max Activating Token Index: 20
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.5886. Min Range: -3.5886
Max Act: 3.3693. Min Act: -0.1700
Data Index: 7770481 (Open Web Text)
Max Activating Token Index: 59
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.5886. Min Range: -3.5886
Max Act: 3.3379. Min Act: -0.1700
Data Index: 6252700 (Open Web Text)
Max Activating Token Index: 57
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.5886. Min Range: -3.5886
Max Act: 3.3065. Min Act: -0.1700
Data Index: 8526708 (Open Web Text)
Max Activating Token Index: 23
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.5886. Min Range: -3.5886
Max Act: 3.3065. Min Act: -0.1700
Data Index: 4225356 (Open Web Text)
Max Activating Token Index: 31
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.5886. Min Range: -3.5886
Max Act: 3.2437. Min Act: -0.1700
Data Index: 7251013 (Open Web Text)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.5886. Min Range: -3.5886
Max Act: 3.2751. Min Act: -0.1700
Data Index: 7689043 (Open Web Text)
Max Activating Token Index: 33
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.5886. Min Range: -3.5886
Max Act: 3.2751. Min Act: -0.1700
Data Index: 2545996 (Open Web Text)
Max Activating Token Index: 35
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.5886. Min Range: -3.5886
Max Act: 3.2437. Min Act: -0.1700
Data Index: 8708449 (Open Web Text)
Max Activating Token Index: 16
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.5886. Min Range: -3.5886
Max Act: 3.2437. Min Act: -0.1700
Data Index: 3105558 (Open Web Text)
Max Activating Token Index: 25
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.5886. Min Range: -3.5886
Max Act: 3.2123. Min Act: -0.1700
Data Index: 5015796 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.5886. Min Range: -3.5886
Max Act: 3.2123. Min Act: -0.1700
Data Index: 1483808 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.5886. Min Range: -3.5886
Max Act: 3.2123. Min Act: -0.1700
Data Index: 979870 (Open Web Text)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #19