Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2228 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.0338. Min Range: -3.0338
Max Act: 3.0338. Min Act: -0.1700
Data Index: 389472 (Open Web Text)
Max Activating Token Index: 738
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.0338. Min Range: -3.0338
Max Act: 2.9231. Min Act: -0.1700
Data Index: 4482105 (Open Web Text)
Max Activating Token Index: 115
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.0338. Min Range: -3.0338
Max Act: 2.9073. Min Act: -0.1700
Data Index: 4869573 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.0338. Min Range: -3.0338
Max Act: 2.8914. Min Act: -0.1700
Data Index: 4084436 (Open Web Text)
Max Activating Token Index: 623
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.0338. Min Range: -3.0338
Max Act: 2.8914. Min Act: -0.1700
Data Index: 7515144 (Open Web Text)
Max Activating Token Index: 328
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.0338. Min Range: -3.0338
Max Act: 2.8914. Min Act: -0.1700
Data Index: 3426524 (Open Web Text)
Max Activating Token Index: 171
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.0338. Min Range: -3.0338
Max Act: 2.8756. Min Act: -0.1700
Data Index: 4873071 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.0338. Min Range: -3.0338
Max Act: 2.8756. Min Act: -0.1700
Data Index: 5486828 (Open Web Text)
Max Activating Token Index: 888
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.0338. Min Range: -3.0338
Max Act: 2.8597. Min Act: -0.1700
Data Index: 7515141 (Open Web Text)
Max Activating Token Index: 390
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.0338. Min Range: -3.0338
Max Act: 2.8597. Min Act: -0.1700
Data Index: 1372496 (Open Web Text)
Max Activating Token Index: 750
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.0338. Min Range: -3.0338
Max Act: 2.8597. Min Act: -0.1700
Data Index: 7147927 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.0338. Min Range: -3.0338
Max Act: 2.8597. Min Act: -0.1700
Data Index: 1121820 (Open Web Text)
Max Activating Token Index: 28
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.0338. Min Range: -3.0338
Max Act: 2.8597. Min Act: -0.1700
Data Index: 4658402 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.0338. Min Range: -3.0338
Max Act: 2.8597. Min Act: -0.1700
Data Index: 98227 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.0338. Min Range: -3.0338
Max Act: 2.8438. Min Act: -0.1700
Data Index: 6228646 (Open Web Text)
Max Activating Token Index: 113
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.0338. Min Range: -3.0338
Max Act: 2.8438. Min Act: -0.1700
Data Index: 7797420 (Open Web Text)
Max Activating Token Index: 581
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.0338. Min Range: -3.0338
Max Act: 2.8438. Min Act: -0.1700
Data Index: 103147 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.0338. Min Range: -3.0338
Max Act: 2.8438. Min Act: -0.1700
Data Index: 5681146 (Open Web Text)
Max Activating Token Index: 250
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.0338. Min Range: -3.0338
Max Act: 2.8438. Min Act: -0.1700
Data Index: 246688 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.0338. Min Range: -3.0338
Max Act: 2.8438. Min Act: -0.1700
Data Index: 8654520 (Open Web Text)
Max Activating Token Index: 145
Click toggle to see full text
Truncated
Full Text #19