Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4169 in Layer 37
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.7349. Min Range: -6.7349
Max Act: 6.7349. Min Act: -0.1700
Data Index: 91664 (Open Web Text)
Max Activating Token Index: 749
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.7349. Min Range: -6.7349
Max Act: 6.6724. Min Act: -0.1700
Data Index: 7888636 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.7349. Min Range: -6.7349
Max Act: 6.3599. Min Act: -0.1700
Data Index: 2149015 (Open Web Text)
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.7349. Min Range: -6.7349
Max Act: 6.2974. Min Act: -0.1700
Data Index: 3387619 (Open Web Text)
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.7349. Min Range: -6.7349
Max Act: 6.2349. Min Act: -0.1700
Data Index: 3721950 (Open Web Text)
Max Activating Token Index: 397
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.7349. Min Range: -6.7349
Max Act: 6.2349. Min Act: -0.1700
Data Index: 369915 (Open Web Text)
Max Activating Token Index: 388
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.7349. Min Range: -6.7349
Max Act: 6.1099. Min Act: -0.1700
Data Index: 554105 (Open Web Text)
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.7349. Min Range: -6.7349
Max Act: 6.0787. Min Act: -0.1700
Data Index: 405049 (Open Web Text)
Max Activating Token Index: 115
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.7349. Min Range: -6.7349
Max Act: 6.0787. Min Act: -0.1700
Data Index: 809421 (Open Web Text)
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.7349. Min Range: -6.7349
Max Act: 6.1099. Min Act: -0.1700
Data Index: 4621230 (Open Web Text)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.7349. Min Range: -6.7349
Max Act: 6.0474. Min Act: -0.1700
Data Index: 7434476 (Open Web Text)
Max Activating Token Index: 708
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.7349. Min Range: -6.7349
Max Act: 6.0162. Min Act: -0.1700
Data Index: 1413442 (Open Web Text)
Max Activating Token Index: 586
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.7349. Min Range: -6.7349
Max Act: 5.9537. Min Act: -0.1700
Data Index: 8550829 (Open Web Text)
Max Activating Token Index: 449
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.7349. Min Range: -6.7349
Max Act: 5.9849. Min Act: -0.1700
Data Index: 5493585 (Open Web Text)
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.7349. Min Range: -6.7349
Max Act: 5.9537. Min Act: -0.1700
Data Index: 7021732 (Open Web Text)
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.7349. Min Range: -6.7349
Max Act: 5.9537. Min Act: -0.1700
Data Index: 572300 (Open Web Text)
Max Activating Token Index: 278
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.7349. Min Range: -6.7349
Max Act: 5.9537. Min Act: -0.1700
Data Index: 6675482 (Open Web Text)
Max Activating Token Index: 607
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.7349. Min Range: -6.7349
Max Act: 5.9224. Min Act: -0.1700
Data Index: 2896299 (Open Web Text)
Max Activating Token Index: 809
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.7349. Min Range: -6.7349
Max Act: 5.8599. Min Act: -0.1700
Data Index: 1586315 (Open Web Text)
Max Activating Token Index: 922
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.7349. Min Range: -6.7349
Max Act: 5.8599. Min Act: -0.1700
Data Index: 3939228 (Open Web Text)
Max Activating Token Index: 710
Click toggle to see full text
Truncated
Full Text #19