Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2210 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.0401. Min Range: -5.0401
Max Act: 5.0401. Min Act: -0.1700
Data Index: 4220674 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0401. Min Range: -5.0401
Max Act: 4.9776. Min Act: -0.1700
Data Index: 4962405 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0401. Min Range: -5.0401
Max Act: 4.9776. Min Act: -0.1700
Data Index: 4745301 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0401. Min Range: -5.0401
Max Act: 4.9463. Min Act: -0.1700
Data Index: 938505 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0401. Min Range: -5.0401
Max Act: 4.9463. Min Act: -0.1700
Data Index: 8488115 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0401. Min Range: -5.0401
Max Act: 4.9463. Min Act: -0.1700
Data Index: 1504917 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0401. Min Range: -5.0401
Max Act: 4.9151. Min Act: -0.1700
Data Index: 4560642 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0401. Min Range: -5.0401
Max Act: 4.9151. Min Act: -0.1700
Data Index: 5028509 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0401. Min Range: -5.0401
Max Act: 4.9151. Min Act: -0.1700
Data Index: 457514 (Open Web Text)
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0401. Min Range: -5.0401
Max Act: 4.9151. Min Act: -0.1700
Data Index: 414230 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0401. Min Range: -5.0401
Max Act: 4.9151. Min Act: -0.1700
Data Index: 5590242 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0401. Min Range: -5.0401
Max Act: 4.9151. Min Act: -0.1700
Data Index: 4549385 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0401. Min Range: -5.0401
Max Act: 4.9151. Min Act: -0.1700
Data Index: 3876472 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0401. Min Range: -5.0401
Max Act: 4.9151. Min Act: -0.1700
Data Index: 3301496 (Open Web Text)
Max Activating Token Index: 42
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0401. Min Range: -5.0401
Max Act: 4.8838. Min Act: -0.1700
Data Index: 1563420 (Open Web Text)
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0401. Min Range: -5.0401
Max Act: 4.8526. Min Act: -0.1700
Data Index: 8524808 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0401. Min Range: -5.0401
Max Act: 4.8838. Min Act: -0.1700
Data Index: 4121924 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0401. Min Range: -5.0401
Max Act: 4.8838. Min Act: -0.1700
Data Index: 3144309 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0401. Min Range: -5.0401
Max Act: 4.8213. Min Act: -0.1700
Data Index: 4862820 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0401. Min Range: -5.0401
Max Act: 4.8526. Min Act: -0.1700
Data Index: 905400 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #19