Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4799 in Layer 38
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.3278. Min Range: -9.3278
Max Act: 9.3278. Min Act: -0.1700
Data Index: 894595 (Open Web Text)
Max Activating Token Index: 108
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.3278. Min Range: -9.3278
Max Act: 8.8278. Min Act: -0.1700
Data Index: 4603151 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.3278. Min Range: -9.3278
Max Act: 8.7028. Min Act: -0.1700
Data Index: 5309327 (Open Web Text)
Max Activating Token Index: 281
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.3278. Min Range: -9.3278
Max Act: 8.3278. Min Act: -0.1700
Data Index: 4556614 (Open Web Text)
Max Activating Token Index: 493
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.3278. Min Range: -9.3278
Max Act: 8.1403. Min Act: -0.1700
Data Index: 2718963 (Open Web Text)
Max Activating Token Index: 484
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.3278. Min Range: -9.3278
Max Act: 8.0778. Min Act: -0.1700
Data Index: 2566146 (Open Web Text)
Max Activating Token Index: 732
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.3278. Min Range: -9.3278
Max Act: 8.0153. Min Act: -0.1700
Data Index: 4644920 (Open Web Text)
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.3278. Min Range: -9.3278
Max Act: 8.0153. Min Act: -0.1700
Data Index: 8528807 (Open Web Text)
Max Activating Token Index: 496
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.3278. Min Range: -9.3278
Max Act: 7.9528. Min Act: -0.1700
Data Index: 1718292 (Open Web Text)
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.3278. Min Range: -9.3278
Max Act: 7.9528. Min Act: -0.1700
Data Index: 2102847 (Open Web Text)
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.3278. Min Range: -9.3278
Max Act: 7.9528. Min Act: -0.1700
Data Index: 8340020 (Open Web Text)
Max Activating Token Index: 395
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.3278. Min Range: -9.3278
Max Act: 7.8903. Min Act: -0.1700
Data Index: 4902873 (Open Web Text)
Max Activating Token Index: 326
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.3278. Min Range: -9.3278
Max Act: 7.8903. Min Act: -0.1700
Data Index: 64447 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.3278. Min Range: -9.3278
Max Act: 7.8903. Min Act: -0.1700
Data Index: 407636 (Open Web Text)
Max Activating Token Index: 918
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.3278. Min Range: -9.3278
Max Act: 7.8278. Min Act: -0.1700
Data Index: 4398677 (Open Web Text)
Max Activating Token Index: 358
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.3278. Min Range: -9.3278
Max Act: 7.8278. Min Act: -0.1700
Data Index: 536720 (Open Web Text)
Max Activating Token Index: 274
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.3278. Min Range: -9.3278
Max Act: 7.8278. Min Act: -0.1700
Data Index: 5315678 (Open Web Text)
Max Activating Token Index: 125
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.3278. Min Range: -9.3278
Max Act: 7.7653. Min Act: -0.1700
Data Index: 3436705 (Open Web Text)
Max Activating Token Index: 686
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.3278. Min Range: -9.3278
Max Act: 7.8278. Min Act: -0.1700
Data Index: 5323566 (Open Web Text)
Max Activating Token Index: 628
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.3278. Min Range: -9.3278
Max Act: 7.8278. Min Act: -0.1700
Data Index: 2514602 (Open Web Text)
Max Activating Token Index: 875
Click toggle to see full text
Truncated
Full Text #19