Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1574 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.6488. Min Range: -4.6488
Max Act: 4.6488. Min Act: -0.1700
Data Index: 4559638 (Open Web Text)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.6488. Min Range: -4.6488
Max Act: 4.5551. Min Act: -0.1700
Data Index: 5325419 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.6488. Min Range: -4.6488
Max Act: 4.5551. Min Act: -0.1700
Data Index: 7714891 (Open Web Text)
Max Activating Token Index: 402
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.6488. Min Range: -4.6488
Max Act: 4.5238. Min Act: -0.1700
Data Index: 583762 (Open Web Text)
Max Activating Token Index: 368
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.6488. Min Range: -4.6488
Max Act: 4.4301. Min Act: -0.1700
Data Index: 23708 (Open Web Text)
Max Activating Token Index: 943
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.6488. Min Range: -4.6488
Max Act: 4.4301. Min Act: -0.1700
Data Index: 4912758 (Open Web Text)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.6488. Min Range: -4.6488
Max Act: 4.4301. Min Act: -0.1700
Data Index: 2787680 (Open Web Text)
Max Activating Token Index: 165
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.6488. Min Range: -4.6488
Max Act: 4.3676. Min Act: -0.1700
Data Index: 7579112 (Open Web Text)
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.6488. Min Range: -4.6488
Max Act: 4.3988. Min Act: -0.1700
Data Index: 8454333 (Open Web Text)
Max Activating Token Index: 756
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.6488. Min Range: -4.6488
Max Act: 4.3988. Min Act: -0.1700
Data Index: 4039137 (Open Web Text)
Max Activating Token Index: 383
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.6488. Min Range: -4.6488
Max Act: 4.3676. Min Act: -0.1700
Data Index: 2632442 (Open Web Text)
Max Activating Token Index: 461
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.6488. Min Range: -4.6488
Max Act: 4.3676. Min Act: -0.1700
Data Index: 6145032 (Open Web Text)
Max Activating Token Index: 897
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.6488. Min Range: -4.6488
Max Act: 4.3363. Min Act: -0.1700
Data Index: 8671430 (Open Web Text)
Max Activating Token Index: 891
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.6488. Min Range: -4.6488
Max Act: 4.3051. Min Act: -0.1700
Data Index: 8218839 (Open Web Text)
Max Activating Token Index: 48
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.6488. Min Range: -4.6488
Max Act: 4.2738. Min Act: -0.1700
Data Index: 1319527 (Open Web Text)
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.6488. Min Range: -4.6488
Max Act: 4.2738. Min Act: -0.1700
Data Index: 4040297 (Open Web Text)
Max Activating Token Index: 253
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.6488. Min Range: -4.6488
Max Act: 4.2113. Min Act: -0.1700
Data Index: 6666275 (Open Web Text)
Max Activating Token Index: 491
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.6488. Min Range: -4.6488
Max Act: 4.2426. Min Act: -0.1700
Data Index: 5225052 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.6488. Min Range: -4.6488
Max Act: 4.2738. Min Act: -0.1700
Data Index: 6422488 (Open Web Text)
Max Activating Token Index: 1008
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.6488. Min Range: -4.6488
Max Act: 4.2426. Min Act: -0.1700
Data Index: 4928167 (Open Web Text)
Max Activating Token Index: 927
Click toggle to see full text
Truncated
Full Text #19