Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5884 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 16.8377. Min Range: -16.8377
Max Act: 16.8377. Min Act: -0.1700
Data Index: 2829730 (Open Web Text)
Max Activating Token Index: 775
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 16.8377. Min Range: -16.8377
Max Act: 16.4627. Min Act: -0.1700
Data Index: 44901 (Open Web Text)
Max Activating Token Index: 672
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 16.8377. Min Range: -16.8377
Max Act: 15.7752. Min Act: -0.1700
Data Index: 4028755 (Open Web Text)
Max Activating Token Index: 206
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 16.8377. Min Range: -16.8377
Max Act: 15.7127. Min Act: -0.1700
Data Index: 2089334 (Open Web Text)
Max Activating Token Index: 281
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 16.8377. Min Range: -16.8377
Max Act: 15.5877. Min Act: -0.1700
Data Index: 7359150 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 16.8377. Min Range: -16.8377
Max Act: 15.5877. Min Act: -0.1700
Data Index: 4820752 (Open Web Text)
Max Activating Token Index: 611
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 16.8377. Min Range: -16.8377
Max Act: 15.5877. Min Act: -0.1700
Data Index: 8393944 (Open Web Text)
Max Activating Token Index: 602
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 16.8377. Min Range: -16.8377
Max Act: 15.4627. Min Act: -0.1700
Data Index: 5970917 (Open Web Text)
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 16.8377. Min Range: -16.8377
Max Act: 15.3377. Min Act: -0.1700
Data Index: 6433782 (Open Web Text)
Max Activating Token Index: 1006
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 16.8377. Min Range: -16.8377
Max Act: 15.3377. Min Act: -0.1700
Data Index: 3762428 (Open Web Text)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 16.8377. Min Range: -16.8377
Max Act: 15.2752. Min Act: -0.1700
Data Index: 7055251 (Open Web Text)
Max Activating Token Index: 317
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 16.8377. Min Range: -16.8377
Max Act: 15.2752. Min Act: -0.1700
Data Index: 4277534 (Open Web Text)
Max Activating Token Index: 755
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 16.8377. Min Range: -16.8377
Max Act: 15.2752. Min Act: -0.1700
Data Index: 839530 (Open Web Text)
Max Activating Token Index: 447
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 16.8377. Min Range: -16.8377
Max Act: 15.0877. Min Act: -0.1700
Data Index: 1208121 (Open Web Text)
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 16.8377. Min Range: -16.8377
Max Act: 15.1502. Min Act: -0.1700
Data Index: 839548 (Open Web Text)
Max Activating Token Index: 484
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 16.8377. Min Range: -16.8377
Max Act: 15.0252. Min Act: -0.1700
Data Index: 3922350 (Open Web Text)
Max Activating Token Index: 798
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 16.8377. Min Range: -16.8377
Max Act: 15.0252. Min Act: -0.1700
Data Index: 8573620 (Open Web Text)
Max Activating Token Index: 680
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 16.8377. Min Range: -16.8377
Max Act: 15.0252. Min Act: -0.1700
Data Index: 2135272 (Open Web Text)
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 16.8377. Min Range: -16.8377
Max Act: 15.0252. Min Act: -0.1700
Data Index: 1204138 (Open Web Text)
Max Activating Token Index: 792
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 16.8377. Min Range: -16.8377
Max Act: 15.0252. Min Act: -0.1700
Data Index: 6024562 (Open Web Text)
Max Activating Token Index: 252
Click toggle to see full text
Truncated
Full Text #19