Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3030 in Layer 30
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.2461. Min Range: -6.2461
Max Act: 6.2461. Min Act: -0.1700
Data Index: 8550431 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.2461. Min Range: -6.2461
Max Act: 6.1836. Min Act: -0.1700
Data Index: 846881 (Open Web Text)
Max Activating Token Index: 689
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.2461. Min Range: -6.2461
Max Act: 6.1836. Min Act: -0.1700
Data Index: 6810025 (Open Web Text)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.2461. Min Range: -6.2461
Max Act: 6.1523. Min Act: -0.1700
Data Index: 4102304 (Open Web Text)
Max Activating Token Index: 418
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.2461. Min Range: -6.2461
Max Act: 6.1523. Min Act: -0.1700
Data Index: 5763312 (Open Web Text)
Max Activating Token Index: 704
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.2461. Min Range: -6.2461
Max Act: 6.0586. Min Act: -0.1700
Data Index: 854295 (Open Web Text)
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.2461. Min Range: -6.2461
Max Act: 5.9961. Min Act: -0.1700
Data Index: 739083 (Open Web Text)
Max Activating Token Index: 50
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.2461. Min Range: -6.2461
Max Act: 5.9961. Min Act: -0.1700
Data Index: 7318032 (Open Web Text)
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.2461. Min Range: -6.2461
Max Act: 5.9961. Min Act: -0.1700
Data Index: 7199658 (Open Web Text)
Max Activating Token Index: 388
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.2461. Min Range: -6.2461
Max Act: 5.9961. Min Act: -0.1700
Data Index: 3803763 (Open Web Text)
Max Activating Token Index: 118
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.2461. Min Range: -6.2461
Max Act: 5.9336. Min Act: -0.1700
Data Index: 5563882 (Open Web Text)
Max Activating Token Index: 788
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.2461. Min Range: -6.2461
Max Act: 5.8711. Min Act: -0.1700
Data Index: 7464867 (Open Web Text)
Max Activating Token Index: 633
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.2461. Min Range: -6.2461
Max Act: 5.9023. Min Act: -0.1700
Data Index: 2577327 (Open Web Text)
Max Activating Token Index: 895
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.2461. Min Range: -6.2461
Max Act: 5.9023. Min Act: -0.1700
Data Index: 3888822 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.2461. Min Range: -6.2461
Max Act: 5.8711. Min Act: -0.1700
Data Index: 5032541 (Open Web Text)
Max Activating Token Index: 440
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.2461. Min Range: -6.2461
Max Act: 5.8398. Min Act: -0.1700
Data Index: 7465380 (Open Web Text)
Max Activating Token Index: 664
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.2461. Min Range: -6.2461
Max Act: 5.8398. Min Act: -0.1700
Data Index: 2733372 (Open Web Text)
Max Activating Token Index: 711
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.2461. Min Range: -6.2461
Max Act: 5.7773. Min Act: -0.1700
Data Index: 3602709 (Open Web Text)
Max Activating Token Index: 648
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.2461. Min Range: -6.2461
Max Act: 5.7773. Min Act: -0.1700
Data Index: 3443006 (Open Web Text)
Max Activating Token Index: 884
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.2461. Min Range: -6.2461
Max Act: 5.7773. Min Act: -0.1700
Data Index: 5365336 (Open Web Text)
Max Activating Token Index: 988
Click toggle to see full text
Truncated
Full Text #19