Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3576 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.8348. Min Range: -4.8348
Max Act: 4.8348. Min Act: -0.1700
Data Index: 4448745 (Open Web Text)
Max Activating Token Index: 221
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.8348. Min Range: -4.8348
Max Act: 4.7723. Min Act: -0.1700
Data Index: 7113069 (Open Web Text)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.8348. Min Range: -4.8348
Max Act: 4.6473. Min Act: -0.1700
Data Index: 2644545 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.8348. Min Range: -4.8348
Max Act: 4.5848. Min Act: -0.1700
Data Index: 3850837 (Open Web Text)
Max Activating Token Index: 411
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.8348. Min Range: -4.8348
Max Act: 4.5848. Min Act: -0.1700
Data Index: 3641329 (Open Web Text)
Max Activating Token Index: 694
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.8348. Min Range: -4.8348
Max Act: 4.5848. Min Act: -0.1700
Data Index: 1792322 (Open Web Text)
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.8348. Min Range: -4.8348
Max Act: 4.5848. Min Act: -0.1700
Data Index: 7932410 (Open Web Text)
Max Activating Token Index: 360
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.8348. Min Range: -4.8348
Max Act: 4.5848. Min Act: -0.1700
Data Index: 8400067 (Open Web Text)
Max Activating Token Index: 530
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.8348. Min Range: -4.8348
Max Act: 4.5223. Min Act: -0.1700
Data Index: 7964259 (Open Web Text)
Max Activating Token Index: 985
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.8348. Min Range: -4.8348
Max Act: 4.4910. Min Act: -0.1700
Data Index: 917296 (Open Web Text)
Max Activating Token Index: 802
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.8348. Min Range: -4.8348
Max Act: 4.4598. Min Act: -0.1700
Data Index: 4512023 (Open Web Text)
Max Activating Token Index: 871
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.8348. Min Range: -4.8348
Max Act: 4.3973. Min Act: -0.1700
Data Index: 1130953 (Open Web Text)
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.8348. Min Range: -4.8348
Max Act: 4.3973. Min Act: -0.1700
Data Index: 3579233 (Open Web Text)
Max Activating Token Index: 221
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.8348. Min Range: -4.8348
Max Act: 4.3660. Min Act: -0.1700
Data Index: 6121062 (Open Web Text)
Max Activating Token Index: 612
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.8348. Min Range: -4.8348
Max Act: 4.3973. Min Act: -0.1700
Data Index: 5359209 (Open Web Text)
Max Activating Token Index: 977
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.8348. Min Range: -4.8348
Max Act: 4.3973. Min Act: -0.1700
Data Index: 1745005 (Open Web Text)
Max Activating Token Index: 801
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.8348. Min Range: -4.8348
Max Act: 4.3973. Min Act: -0.1700
Data Index: 203994 (Open Web Text)
Max Activating Token Index: 831
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.8348. Min Range: -4.8348
Max Act: 4.3660. Min Act: -0.1700
Data Index: 705528 (Open Web Text)
Max Activating Token Index: 427
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.8348. Min Range: -4.8348
Max Act: 4.3660. Min Act: -0.1700
Data Index: 8425374 (Open Web Text)
Max Activating Token Index: 858
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.8348. Min Range: -4.8348
Max Act: 4.3973. Min Act: -0.1700
Data Index: 8280437 (Open Web Text)
Max Activating Token Index: 931
Click toggle to see full text
Truncated
Full Text #19