Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4882 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.1600. Min Range: -6.1600
Max Act: 6.1600. Min Act: -0.1700
Data Index: 6976695 (Open Web Text)
Max Activating Token Index: 743
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.1600. Min Range: -6.1600
Max Act: 5.9412. Min Act: -0.1700
Data Index: 6453310 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.1600. Min Range: -6.1600
Max Act: 5.8162. Min Act: -0.1700
Data Index: 7862572 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.1600. Min Range: -6.1600
Max Act: 5.7850. Min Act: -0.1700
Data Index: 7420359 (Open Web Text)
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.1600. Min Range: -6.1600
Max Act: 5.7537. Min Act: -0.1700
Data Index: 3537119 (Open Web Text)
Max Activating Token Index: 260
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.1600. Min Range: -6.1600
Max Act: 5.7225. Min Act: -0.1700
Data Index: 8315271 (Open Web Text)
Max Activating Token Index: 186
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.1600. Min Range: -6.1600
Max Act: 5.5975. Min Act: -0.1700
Data Index: 6345513 (Open Web Text)
Max Activating Token Index: 405
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.1600. Min Range: -6.1600
Max Act: 5.5975. Min Act: -0.1700
Data Index: 7177568 (Open Web Text)
Max Activating Token Index: 712
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.1600. Min Range: -6.1600
Max Act: 5.4725. Min Act: -0.1700
Data Index: 5290708 (Open Web Text)
Max Activating Token Index: 374
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.1600. Min Range: -6.1600
Max Act: 5.5037. Min Act: -0.1700
Data Index: 7951782 (Open Web Text)
Max Activating Token Index: 203
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.1600. Min Range: -6.1600
Max Act: 5.5037. Min Act: -0.1700
Data Index: 7420337 (Open Web Text)
Max Activating Token Index: 156
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.1600. Min Range: -6.1600
Max Act: 5.5037. Min Act: -0.1700
Data Index: 6925168 (Open Web Text)
Max Activating Token Index: 513
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.1600. Min Range: -6.1600
Max Act: 5.5037. Min Act: -0.1700
Data Index: 715581 (Open Web Text)
Max Activating Token Index: 386
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.1600. Min Range: -6.1600
Max Act: 5.4100. Min Act: -0.1700
Data Index: 2527558 (Open Web Text)
Max Activating Token Index: 123
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.1600. Min Range: -6.1600
Max Act: 5.3787. Min Act: -0.1700
Data Index: 337129 (Open Web Text)
Max Activating Token Index: 333
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.1600. Min Range: -6.1600
Max Act: 5.3787. Min Act: -0.1700
Data Index: 8633720 (Open Web Text)
Max Activating Token Index: 144
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.1600. Min Range: -6.1600
Max Act: 5.3475. Min Act: -0.1700
Data Index: 1671803 (Open Web Text)
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.1600. Min Range: -6.1600
Max Act: 5.3475. Min Act: -0.1700
Data Index: 4415723 (Open Web Text)
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.1600. Min Range: -6.1600
Max Act: 5.3475. Min Act: -0.1700
Data Index: 3478101 (Open Web Text)
Max Activating Token Index: 419
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.1600. Min Range: -6.1600
Max Act: 5.3475. Min Act: -0.1700
Data Index: 3363621 (Open Web Text)
Max Activating Token Index: 721
Click toggle to see full text
Truncated
Full Text #19