Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 386 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.3479. Min Range: -5.3479
Max Act: 5.3479. Min Act: -0.1700
Data Index: 736710 (Open Web Text)
Max Activating Token Index: 315
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.3479. Min Range: -5.3479
Max Act: 5.2854. Min Act: -0.1700
Data Index: 7000514 (Open Web Text)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.3479. Min Range: -5.3479
Max Act: 5.3167. Min Act: -0.1700
Data Index: 3284509 (Open Web Text)
Max Activating Token Index: 158
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.3479. Min Range: -5.3479
Max Act: 5.2854. Min Act: -0.1700
Data Index: 1941926 (Open Web Text)
Max Activating Token Index: 374
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.3479. Min Range: -5.3479
Max Act: 5.2542. Min Act: -0.1700
Data Index: 4909999 (Open Web Text)
Max Activating Token Index: 66
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.3479. Min Range: -5.3479
Max Act: 5.2542. Min Act: -0.1700
Data Index: 6671922 (Open Web Text)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.3479. Min Range: -5.3479
Max Act: 5.2229. Min Act: -0.1700
Data Index: 138350 (Open Web Text)
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.3479. Min Range: -5.3479
Max Act: 5.1604. Min Act: -0.1700
Data Index: 3027428 (Open Web Text)
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.3479. Min Range: -5.3479
Max Act: 5.1604. Min Act: -0.1700
Data Index: 1292505 (Open Web Text)
Max Activating Token Index: 710
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.3479. Min Range: -5.3479
Max Act: 5.1292. Min Act: -0.1700
Data Index: 3976115 (Open Web Text)
Max Activating Token Index: 474
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.3479. Min Range: -5.3479
Max Act: 5.1292. Min Act: -0.1700
Data Index: 5312066 (Open Web Text)
Max Activating Token Index: 440
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.3479. Min Range: -5.3479
Max Act: 5.1292. Min Act: -0.1700
Data Index: 5502687 (Open Web Text)
Max Activating Token Index: 604
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.3479. Min Range: -5.3479
Max Act: 5.0667. Min Act: -0.1700
Data Index: 7272054 (Open Web Text)
Max Activating Token Index: 961
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.3479. Min Range: -5.3479
Max Act: 5.0979. Min Act: -0.1700
Data Index: 6651506 (Open Web Text)
Max Activating Token Index: 643
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.3479. Min Range: -5.3479
Max Act: 5.0667. Min Act: -0.1700
Data Index: 1765732 (Open Web Text)
Max Activating Token Index: 37
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.3479. Min Range: -5.3479
Max Act: 5.0667. Min Act: -0.1700
Data Index: 7945240 (Open Web Text)
Max Activating Token Index: 622
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.3479. Min Range: -5.3479
Max Act: 5.0354. Min Act: -0.1700
Data Index: 3885585 (Open Web Text)
Max Activating Token Index: 237
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.3479. Min Range: -5.3479
Max Act: 5.0354. Min Act: -0.1700
Data Index: 1974849 (Open Web Text)
Max Activating Token Index: 46
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.3479. Min Range: -5.3479
Max Act: 5.0667. Min Act: -0.1696
Data Index: 3699509 (Open Web Text)
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.3479. Min Range: -5.3479
Max Act: 5.0667. Min Act: -0.1700
Data Index: 4183380 (Open Web Text)
Max Activating Token Index: 493
Click toggle to see full text
Truncated
Full Text #19