Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2896 in Layer 13
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.9732. Min Range: -5.9732
Max Act: 5.9732. Min Act: -0.1700
Data Index: 3977675 (Open Web Text)
Max Activating Token Index: 990
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9732. Min Range: -5.9732
Max Act: 5.6295. Min Act: -0.1700
Data Index: 4827015 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9732. Min Range: -5.9732
Max Act: 5.4732. Min Act: -0.1700
Data Index: 1596734 (Open Web Text)
Max Activating Token Index: 384
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9732. Min Range: -5.9732
Max Act: 5.4732. Min Act: -0.1700
Data Index: 5056570 (Open Web Text)
Max Activating Token Index: 899
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9732. Min Range: -5.9732
Max Act: 5.3482. Min Act: -0.1700
Data Index: 5557564 (Open Web Text)
Max Activating Token Index: 816
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9732. Min Range: -5.9732
Max Act: 5.3170. Min Act: -0.1700
Data Index: 3378485 (Open Web Text)
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9732. Min Range: -5.9732
Max Act: 5.3170. Min Act: -0.1700
Data Index: 831127 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9732. Min Range: -5.9732
Max Act: 5.3170. Min Act: -0.1700
Data Index: 454918 (Open Web Text)
Max Activating Token Index: 832
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9732. Min Range: -5.9732
Max Act: 5.2545. Min Act: -0.1700
Data Index: 2756565 (Open Web Text)
Max Activating Token Index: 549
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9732. Min Range: -5.9732
Max Act: 5.2545. Min Act: -0.1700
Data Index: 3031080 (Open Web Text)
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9732. Min Range: -5.9732
Max Act: 5.2232. Min Act: -0.1700
Data Index: 4421301 (Open Web Text)
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9732. Min Range: -5.9732
Max Act: 5.2545. Min Act: -0.1700
Data Index: 8677701 (Open Web Text)
Max Activating Token Index: 506
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9732. Min Range: -5.9732
Max Act: 5.2232. Min Act: -0.1700
Data Index: 3392422 (Open Web Text)
Max Activating Token Index: 769
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9732. Min Range: -5.9732
Max Act: 5.2232. Min Act: -0.1700
Data Index: 3620120 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9732. Min Range: -5.9732
Max Act: 5.2232. Min Act: -0.1700
Data Index: 5179155 (Open Web Text)
Max Activating Token Index: 829
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9732. Min Range: -5.9732
Max Act: 5.2232. Min Act: -0.1700
Data Index: 1356748 (Open Web Text)
Max Activating Token Index: 730
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9732. Min Range: -5.9732
Max Act: 5.2232. Min Act: -0.1700
Data Index: 7047315 (Open Web Text)
Max Activating Token Index: 626
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9732. Min Range: -5.9732
Max Act: 5.1920. Min Act: -0.1700
Data Index: 394941 (Open Web Text)
Max Activating Token Index: 797
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9732. Min Range: -5.9732
Max Act: 5.1920. Min Act: -0.1700
Data Index: 247917 (Open Web Text)
Max Activating Token Index: 717
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9732. Min Range: -5.9732
Max Act: 5.1920. Min Act: -0.1700
Data Index: 4774141 (Open Web Text)
Max Activating Token Index: 299
Click toggle to see full text
Truncated
Full Text #19