Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3575 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.3084. Min Range: -7.3084
Max Act: 7.3084. Min Act: -0.1700
Data Index: 2873793 (Open Web Text)
Max Activating Token Index: 511
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.3084. Min Range: -7.3084
Max Act: 7.1834. Min Act: -0.1700
Data Index: 585653 (Open Web Text)
Max Activating Token Index: 530
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.3084. Min Range: -7.3084
Max Act: 6.9959. Min Act: -0.1700
Data Index: 1373883 (Open Web Text)
Max Activating Token Index: 348
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.3084. Min Range: -7.3084
Max Act: 6.9334. Min Act: -0.1700
Data Index: 661283 (Open Web Text)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.3084. Min Range: -7.3084
Max Act: 6.4334. Min Act: -0.1700
Data Index: 5397586 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.3084. Min Range: -7.3084
Max Act: 6.4334. Min Act: -0.1700
Data Index: 2174353 (Open Web Text)
Max Activating Token Index: 556
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.3084. Min Range: -7.3084
Max Act: 6.4334. Min Act: -0.1700
Data Index: 6886743 (Open Web Text)
Max Activating Token Index: 254
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.3084. Min Range: -7.3084
Max Act: 6.3709. Min Act: -0.1700
Data Index: 4328367 (Open Web Text)
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.3084. Min Range: -7.3084
Max Act: 6.3709. Min Act: -0.1700
Data Index: 7898979 (Open Web Text)
Max Activating Token Index: 496
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.3084. Min Range: -7.3084
Max Act: 6.3709. Min Act: -0.1700
Data Index: 2349480 (Open Web Text)
Max Activating Token Index: 807
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.3084. Min Range: -7.3084
Max Act: 6.3397. Min Act: -0.1700
Data Index: 1117184 (Open Web Text)
Max Activating Token Index: 319
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.3084. Min Range: -7.3084
Max Act: 6.3397. Min Act: -0.1700
Data Index: 3847831 (Open Web Text)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.3084. Min Range: -7.3084
Max Act: 6.3709. Min Act: -0.1700
Data Index: 1192214 (Open Web Text)
Max Activating Token Index: 984
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.3084. Min Range: -7.3084
Max Act: 6.3397. Min Act: -0.1700
Data Index: 3492128 (Open Web Text)
Max Activating Token Index: 443
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.3084. Min Range: -7.3084
Max Act: 6.3084. Min Act: -0.1700
Data Index: 2287710 (Open Web Text)
Max Activating Token Index: 551
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.3084. Min Range: -7.3084
Max Act: 6.3084. Min Act: -0.1700
Data Index: 4877566 (Open Web Text)
Max Activating Token Index: 763
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.3084. Min Range: -7.3084
Max Act: 6.3084. Min Act: -0.1700
Data Index: 7105075 (Open Web Text)
Max Activating Token Index: 1019
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.3084. Min Range: -7.3084
Max Act: 6.2772. Min Act: -0.1700
Data Index: 2424178 (Open Web Text)
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.3084. Min Range: -7.3084
Max Act: 6.2772. Min Act: -0.1700
Data Index: 7114747 (Open Web Text)
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.3084. Min Range: -7.3084
Max Act: 6.2772. Min Act: -0.1700
Data Index: 7193381 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #19