Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2983 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.4274. Min Range: -9.4274
Max Act: 9.4274. Min Act: -0.1700
Data Index: 5613551 (Open Web Text)
Max Activating Token Index: 357
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.4274. Min Range: -9.4274
Max Act: 9.3024. Min Act: -0.1700
Data Index: 506762 (Open Web Text)
Max Activating Token Index: 891
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.4274. Min Range: -9.4274
Max Act: 9.2399. Min Act: -0.1700
Data Index: 939711 (Open Web Text)
Max Activating Token Index: 101
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.4274. Min Range: -9.4274
Max Act: 9.0524. Min Act: -0.1700
Data Index: 4239209 (Open Web Text)
Max Activating Token Index: 797
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.4274. Min Range: -9.4274
Max Act: 8.9899. Min Act: -0.1700
Data Index: 6554782 (Open Web Text)
Max Activating Token Index: 443
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.4274. Min Range: -9.4274
Max Act: 8.9274. Min Act: -0.1700
Data Index: 3174055 (Open Web Text)
Max Activating Token Index: 994
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.4274. Min Range: -9.4274
Max Act: 8.9274. Min Act: -0.1700
Data Index: 5189721 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.4274. Min Range: -9.4274
Max Act: 8.8649. Min Act: -0.1700
Data Index: 265824 (Open Web Text)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.4274. Min Range: -9.4274
Max Act: 8.8649. Min Act: -0.1700
Data Index: 1210510 (Open Web Text)
Max Activating Token Index: 236
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.4274. Min Range: -9.4274
Max Act: 8.8024. Min Act: -0.1700
Data Index: 3734149 (Open Web Text)
Max Activating Token Index: 707
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.4274. Min Range: -9.4274
Max Act: 8.7399. Min Act: -0.1700
Data Index: 1581054 (Open Web Text)
Max Activating Token Index: 826
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.4274. Min Range: -9.4274
Max Act: 8.6774. Min Act: -0.1700
Data Index: 550006 (Open Web Text)
Max Activating Token Index: 427
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.4274. Min Range: -9.4274
Max Act: 8.6774. Min Act: -0.1700
Data Index: 7266356 (Open Web Text)
Max Activating Token Index: 894
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.4274. Min Range: -9.4274
Max Act: 8.6774. Min Act: -0.1700
Data Index: 294538 (Open Web Text)
Max Activating Token Index: 263
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.4274. Min Range: -9.4274
Max Act: 8.6774. Min Act: -0.1700
Data Index: 8502953 (Open Web Text)
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.4274. Min Range: -9.4274
Max Act: 8.5524. Min Act: -0.1700
Data Index: 5563979 (Open Web Text)
Max Activating Token Index: 272
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.4274. Min Range: -9.4274
Max Act: 8.6149. Min Act: -0.1700
Data Index: 5954599 (Open Web Text)
Max Activating Token Index: 629
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.4274. Min Range: -9.4274
Max Act: 8.6774. Min Act: -0.1700
Data Index: 7010812 (Open Web Text)
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.4274. Min Range: -9.4274
Max Act: 8.5524. Min Act: -0.1700
Data Index: 939710 (Open Web Text)
Max Activating Token Index: 755
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.4274. Min Range: -9.4274
Max Act: 8.5524. Min Act: -0.1700
Data Index: 2011402 (Open Web Text)
Max Activating Token Index: 909
Click toggle to see full text
Truncated
Full Text #19