Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1954 in Layer 27
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.9568. Min Range: -7.9568
Max Act: 7.9568. Min Act: -0.1700
Data Index: 3201183 (Open Web Text)
Max Activating Token Index: 756
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.9568. Min Range: -7.9568
Max Act: 7.8318. Min Act: -0.1700
Data Index: 7158018 (Open Web Text)
Max Activating Token Index: 718
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.9568. Min Range: -7.9568
Max Act: 7.6443. Min Act: -0.1700
Data Index: 4117414 (Open Web Text)
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.9568. Min Range: -7.9568
Max Act: 7.5818. Min Act: -0.1700
Data Index: 2750066 (Open Web Text)
Max Activating Token Index: 208
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.9568. Min Range: -7.9568
Max Act: 7.5506. Min Act: -0.1700
Data Index: 3171674 (Open Web Text)
Max Activating Token Index: 741
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.9568. Min Range: -7.9568
Max Act: 7.5818. Min Act: -0.1700
Data Index: 2633382 (Open Web Text)
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.9568. Min Range: -7.9568
Max Act: 7.3943. Min Act: -0.1700
Data Index: 557457 (Open Web Text)
Max Activating Token Index: 802
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.9568. Min Range: -7.9568
Max Act: 7.4256. Min Act: -0.1700
Data Index: 2571461 (Open Web Text)
Max Activating Token Index: 688
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.9568. Min Range: -7.9568
Max Act: 7.3631. Min Act: -0.1700
Data Index: 134150 (Open Web Text)
Max Activating Token Index: 501
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.9568. Min Range: -7.9568
Max Act: 7.3631. Min Act: -0.1700
Data Index: 6581292 (Open Web Text)
Max Activating Token Index: 602
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.9568. Min Range: -7.9568
Max Act: 7.3006. Min Act: -0.1700
Data Index: 1531003 (Open Web Text)
Max Activating Token Index: 630
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.9568. Min Range: -7.9568
Max Act: 7.2381. Min Act: -0.1700
Data Index: 4619979 (Open Web Text)
Max Activating Token Index: 963
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.9568. Min Range: -7.9568
Max Act: 7.2381. Min Act: -0.1700
Data Index: 3594345 (Open Web Text)
Max Activating Token Index: 915
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.9568. Min Range: -7.9568
Max Act: 7.2381. Min Act: -0.1699
Data Index: 1294393 (Open Web Text)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.9568. Min Range: -7.9568
Max Act: 7.2068. Min Act: -0.1700
Data Index: 5070697 (Open Web Text)
Max Activating Token Index: 971
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.9568. Min Range: -7.9568
Max Act: 7.2068. Min Act: -0.1700
Data Index: 1431929 (Open Web Text)
Max Activating Token Index: 878
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.9568. Min Range: -7.9568
Max Act: 7.2068. Min Act: -0.1700
Data Index: 5696525 (Open Web Text)
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.9568. Min Range: -7.9568
Max Act: 7.1756. Min Act: -0.1700
Data Index: 3885656 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.9568. Min Range: -7.9568
Max Act: 7.1756. Min Act: -0.1700
Data Index: 8020232 (Open Web Text)
Max Activating Token Index: 618
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.9568. Min Range: -7.9568
Max Act: 7.1756. Min Act: -0.1700
Data Index: 5772786 (Open Web Text)
Max Activating Token Index: 994
Click toggle to see full text
Truncated
Full Text #19