Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3001 in Layer 30
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.7542. Min Range: -6.7542
Max Act: 6.7542. Min Act: -0.1700
Data Index: 52763 (Open Web Text)
Max Activating Token Index: 835
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.7542. Min Range: -6.7542
Max Act: 6.5667. Min Act: -0.1700
Data Index: 851529 (Open Web Text)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.7542. Min Range: -6.7542
Max Act: 6.5355. Min Act: -0.1700
Data Index: 4539891 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.7542. Min Range: -6.7542
Max Act: 6.5042. Min Act: -0.1700
Data Index: 7091126 (Open Web Text)
Max Activating Token Index: 655
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.7542. Min Range: -6.7542
Max Act: 6.5042. Min Act: -0.1700
Data Index: 3306032 (Open Web Text)
Max Activating Token Index: 819
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.7542. Min Range: -6.7542
Max Act: 6.4417. Min Act: -0.1700
Data Index: 6799320 (Open Web Text)
Max Activating Token Index: 1002
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.7542. Min Range: -6.7542
Max Act: 6.4730. Min Act: -0.1700
Data Index: 1094876 (Open Web Text)
Max Activating Token Index: 278
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.7542. Min Range: -6.7542
Max Act: 6.4105. Min Act: -0.1700
Data Index: 3752538 (Open Web Text)
Max Activating Token Index: 118
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.7542. Min Range: -6.7542
Max Act: 6.3792. Min Act: -0.1700
Data Index: 666544 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.7542. Min Range: -6.7542
Max Act: 6.3792. Min Act: -0.1700
Data Index: 5334570 (Open Web Text)
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.7542. Min Range: -6.7542
Max Act: 6.3480. Min Act: -0.1700
Data Index: 1850837 (Open Web Text)
Max Activating Token Index: 610
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.7542. Min Range: -6.7542
Max Act: 6.3167. Min Act: -0.1700
Data Index: 4487323 (Open Web Text)
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.7542. Min Range: -6.7542
Max Act: 6.3167. Min Act: -0.1700
Data Index: 2193105 (Open Web Text)
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.7542. Min Range: -6.7542
Max Act: 6.2855. Min Act: -0.1700
Data Index: 8119475 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.7542. Min Range: -6.7542
Max Act: 6.2230. Min Act: -0.1700
Data Index: 5074646 (Open Web Text)
Max Activating Token Index: 227
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.7542. Min Range: -6.7542
Max Act: 6.2230. Min Act: -0.1700
Data Index: 218672 (Open Web Text)
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.7542. Min Range: -6.7542
Max Act: 6.2542. Min Act: -0.1700
Data Index: 6529183 (Open Web Text)
Max Activating Token Index: 541
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.7542. Min Range: -6.7542
Max Act: 6.2230. Min Act: -0.1700
Data Index: 1452693 (Open Web Text)
Max Activating Token Index: 1004
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.7542. Min Range: -6.7542
Max Act: 6.2230. Min Act: -0.1700
Data Index: 2436583 (Open Web Text)
Max Activating Token Index: 120
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.7542. Min Range: -6.7542
Max Act: 6.2230. Min Act: -0.1700
Data Index: 6799321 (Open Web Text)
Max Activating Token Index: 120
Click toggle to see full text
Truncated
Full Text #19