Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 595 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.7209. Min Range: -4.7209
Max Act: 4.7209. Min Act: -0.1700
Data Index: 4227823 (Open Web Text)
Max Activating Token Index: 630
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.7209. Min Range: -4.7209
Max Act: 4.6271. Min Act: -0.1700
Data Index: 560486 (Open Web Text)
Max Activating Token Index: 399
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.7209. Min Range: -4.7209
Max Act: 4.5646. Min Act: -0.1700
Data Index: 7430851 (Open Web Text)
Max Activating Token Index: 289
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.7209. Min Range: -4.7209
Max Act: 4.5959. Min Act: -0.1700
Data Index: 8148608 (Open Web Text)
Max Activating Token Index: 39
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.7209. Min Range: -4.7209
Max Act: 4.5646. Min Act: -0.1700
Data Index: 4621811 (Open Web Text)
Max Activating Token Index: 144
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.7209. Min Range: -4.7209
Max Act: 4.5334. Min Act: -0.1700
Data Index: 5177471 (Open Web Text)
Max Activating Token Index: 754
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.7209. Min Range: -4.7209
Max Act: 4.5021. Min Act: -0.1700
Data Index: 7439632 (Open Web Text)
Max Activating Token Index: 39
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.7209. Min Range: -4.7209
Max Act: 4.4709. Min Act: -0.1700
Data Index: 7430849 (Open Web Text)
Max Activating Token Index: 89
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.7209. Min Range: -4.7209
Max Act: 4.4709. Min Act: -0.1700
Data Index: 7207510 (Open Web Text)
Max Activating Token Index: 72
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.7209. Min Range: -4.7209
Max Act: 4.4709. Min Act: -0.1700
Data Index: 5610894 (Open Web Text)
Max Activating Token Index: 88
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.7209. Min Range: -4.7209
Max Act: 4.4396. Min Act: -0.1700
Data Index: 8003021 (Open Web Text)
Max Activating Token Index: 281
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.7209. Min Range: -4.7209
Max Act: 4.4396. Min Act: -0.1700
Data Index: 7207508 (Open Web Text)
Max Activating Token Index: 155
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.7209. Min Range: -4.7209
Max Act: 4.4084. Min Act: -0.1700
Data Index: 8322988 (Open Web Text)
Max Activating Token Index: 769
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.7209. Min Range: -4.7209
Max Act: 4.4396. Min Act: -0.1700
Data Index: 6538692 (Open Web Text)
Max Activating Token Index: 320
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.7209. Min Range: -4.7209
Max Act: 4.4396. Min Act: -0.1700
Data Index: 7572878 (Open Web Text)
Max Activating Token Index: 48
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.7209. Min Range: -4.7209
Max Act: 4.4396. Min Act: -0.1700
Data Index: 7475589 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.7209. Min Range: -4.7209
Max Act: 4.4396. Min Act: -0.1700
Data Index: 8003026 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.7209. Min Range: -4.7209
Max Act: 4.4396. Min Act: -0.1700
Data Index: 7430850 (Open Web Text)
Max Activating Token Index: 92
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.7209. Min Range: -4.7209
Max Act: 4.4396. Min Act: -0.1700
Data Index: 3914351 (Open Web Text)
Max Activating Token Index: 317
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.7209. Min Range: -4.7209
Max Act: 4.4084. Min Act: -0.1700
Data Index: 8003019 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #19