Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4374 in Layer 12
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.6101. Min Range: -5.6101
Max Act: 5.6101. Min Act: -0.1700
Data Index: 553016 (Open Web Text)
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.6101. Min Range: -5.6101
Max Act: 5.5788. Min Act: -0.1700
Data Index: 6690086 (Open Web Text)
Max Activating Token Index: 603
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.6101. Min Range: -5.6101
Max Act: 5.5788. Min Act: -0.1700
Data Index: 6833539 (Open Web Text)
Max Activating Token Index: 732
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.6101. Min Range: -5.6101
Max Act: 5.5476. Min Act: -0.1700
Data Index: 1814925 (Open Web Text)
Max Activating Token Index: 459
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.6101. Min Range: -5.6101
Max Act: 5.5476. Min Act: -0.1700
Data Index: 7713288 (Open Web Text)
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.6101. Min Range: -5.6101
Max Act: 5.5476. Min Act: -0.1700
Data Index: 2811727 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.6101. Min Range: -5.6101
Max Act: 5.5476. Min Act: -0.1700
Data Index: 7132505 (Open Web Text)
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.6101. Min Range: -5.6101
Max Act: 5.5163. Min Act: -0.1700
Data Index: 2143301 (Open Web Text)
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.6101. Min Range: -5.6101
Max Act: 5.5163. Min Act: -0.1700
Data Index: 1564949 (Open Web Text)
Max Activating Token Index: 780
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.6101. Min Range: -5.6101
Max Act: 5.4851. Min Act: -0.1700
Data Index: 3374564 (Open Web Text)
Max Activating Token Index: 743
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.6101. Min Range: -5.6101
Max Act: 5.4851. Min Act: -0.1700
Data Index: 8632403 (Open Web Text)
Max Activating Token Index: 813
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.6101. Min Range: -5.6101
Max Act: 5.4851. Min Act: -0.1700
Data Index: 2232334 (Open Web Text)
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.6101. Min Range: -5.6101
Max Act: 5.4851. Min Act: -0.1700
Data Index: 5734237 (Open Web Text)
Max Activating Token Index: 851
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.6101. Min Range: -5.6101
Max Act: 5.4851. Min Act: -0.1700
Data Index: 6036260 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.6101. Min Range: -5.6101
Max Act: 5.4538. Min Act: -0.1700
Data Index: 7054745 (Open Web Text)
Max Activating Token Index: 958
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.6101. Min Range: -5.6101
Max Act: 5.4538. Min Act: -0.1700
Data Index: 6531815 (Open Web Text)
Max Activating Token Index: 863
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.6101. Min Range: -5.6101
Max Act: 5.4538. Min Act: -0.1700
Data Index: 7922090 (Open Web Text)
Max Activating Token Index: 721
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.6101. Min Range: -5.6101
Max Act: 5.4538. Min Act: -0.1700
Data Index: 6597047 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.6101. Min Range: -5.6101
Max Act: 5.4226. Min Act: -0.1700
Data Index: 6190383 (Open Web Text)
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.6101. Min Range: -5.6101
Max Act: 5.4226. Min Act: -0.1700
Data Index: 5138931 (Open Web Text)
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #19