Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2164 in Layer 39
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.1428. Min Range: -6.1428
Max Act: 6.1428. Min Act: -0.1700
Data Index: 1758981 (Open Web Text)
Max Activating Token Index: 707
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.1428. Min Range: -6.1428
Max Act: 6.0178. Min Act: -0.1700
Data Index: 3877685 (Open Web Text)
Max Activating Token Index: 94
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.1428. Min Range: -6.1428
Max Act: 5.9865. Min Act: -0.1700
Data Index: 1984583 (Open Web Text)
Max Activating Token Index: 373
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.1428. Min Range: -6.1428
Max Act: 5.9865. Min Act: -0.1700
Data Index: 5059975 (Open Web Text)
Max Activating Token Index: 922
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.1428. Min Range: -6.1428
Max Act: 5.9865. Min Act: -0.1700
Data Index: 571692 (Open Web Text)
Max Activating Token Index: 297
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.1428. Min Range: -6.1428
Max Act: 5.9553. Min Act: -0.1700
Data Index: 8536 (Open Web Text)
Max Activating Token Index: 718
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.1428. Min Range: -6.1428
Max Act: 5.8615. Min Act: -0.1700
Data Index: 6980456 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.1428. Min Range: -6.1428
Max Act: 5.8615. Min Act: -0.1700
Data Index: 180159 (Open Web Text)
Max Activating Token Index: 947
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.1428. Min Range: -6.1428
Max Act: 5.7990. Min Act: -0.1700
Data Index: 3622024 (Open Web Text)
Max Activating Token Index: 60
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.1428. Min Range: -6.1428
Max Act: 5.7990. Min Act: -0.1700
Data Index: 2584392 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.1428. Min Range: -6.1428
Max Act: 5.7678. Min Act: -0.1700
Data Index: 4306065 (Open Web Text)
Max Activating Token Index: 85
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.1428. Min Range: -6.1428
Max Act: 5.7678. Min Act: -0.1700
Data Index: 4557245 (Open Web Text)
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.1428. Min Range: -6.1428
Max Act: 5.7990. Min Act: -0.1700
Data Index: 8243762 (Open Web Text)
Max Activating Token Index: 417
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.1428. Min Range: -6.1428
Max Act: 5.7678. Min Act: -0.1700
Data Index: 808564 (Open Web Text)
Max Activating Token Index: 395
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.1428. Min Range: -6.1428
Max Act: 5.7365. Min Act: -0.1700
Data Index: 2342226 (Open Web Text)
Max Activating Token Index: 677
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.1428. Min Range: -6.1428
Max Act: 5.7365. Min Act: -0.1700
Data Index: 4147305 (Open Web Text)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.1428. Min Range: -6.1428
Max Act: 5.7365. Min Act: -0.1700
Data Index: 1975422 (Open Web Text)
Max Activating Token Index: 245
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.1428. Min Range: -6.1428
Max Act: 5.7678. Min Act: -0.1700
Data Index: 3408890 (Open Web Text)
Max Activating Token Index: 250
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.1428. Min Range: -6.1428
Max Act: 5.7365. Min Act: -0.1700
Data Index: 5820902 (Open Web Text)
Max Activating Token Index: 139
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.1428. Min Range: -6.1428
Max Act: 5.7365. Min Act: -0.1700
Data Index: 2418869 (Open Web Text)
Max Activating Token Index: 299
Click toggle to see full text
Truncated
Full Text #19