Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4258 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 2.4424. Min Range: -2.4424
Max Act: 2.4424. Min Act: -0.1700
Data Index: 378914 (Open Web Text)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.4424. Min Range: -2.4424
Max Act: 2.3280. Min Act: -0.1700
Data Index: 6112912 (Open Web Text)
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.4424. Min Range: -2.4424
Max Act: 2.3116. Min Act: -0.1700
Data Index: 8677208 (Open Web Text)
Max Activating Token Index: 126
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.4424. Min Range: -2.4424
Max Act: 2.2787. Min Act: -0.1700
Data Index: 673551 (Open Web Text)
Max Activating Token Index: 405
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.4424. Min Range: -2.4424
Max Act: 2.2787. Min Act: -0.1700
Data Index: 640709 (Open Web Text)
Max Activating Token Index: 988
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.4424. Min Range: -2.4424
Max Act: 2.2622. Min Act: -0.1700
Data Index: 3071777 (Open Web Text)
Max Activating Token Index: 661
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.4424. Min Range: -2.4424
Max Act: 2.2622. Min Act: -0.1700
Data Index: 2285607 (Open Web Text)
Max Activating Token Index: 517
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.4424. Min Range: -2.4424
Max Act: 2.2787. Min Act: -0.1700
Data Index: 1507633 (Open Web Text)
Max Activating Token Index: 699
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.4424. Min Range: -2.4424
Max Act: 2.2457. Min Act: -0.1700
Data Index: 3501453 (Open Web Text)
Max Activating Token Index: 804
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.4424. Min Range: -2.4424
Max Act: 2.2457. Min Act: -0.1700
Data Index: 1788031 (Open Web Text)
Max Activating Token Index: 40
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.4424. Min Range: -2.4424
Max Act: 2.2291. Min Act: -0.1700
Data Index: 6957316 (Open Web Text)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.4424. Min Range: -2.4424
Max Act: 2.2291. Min Act: -0.1700
Data Index: 5076872 (Open Web Text)
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.4424. Min Range: -2.4424
Max Act: 2.2126. Min Act: -0.1700
Data Index: 3816211 (Open Web Text)
Max Activating Token Index: 39
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.4424. Min Range: -2.4424
Max Act: 2.1960. Min Act: -0.1700
Data Index: 4149859 (Open Web Text)
Max Activating Token Index: 346
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.4424. Min Range: -2.4424
Max Act: 2.1794. Min Act: -0.1700
Data Index: 3108000 (Open Web Text)
Max Activating Token Index: 1002
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.4424. Min Range: -2.4424
Max Act: 2.1794. Min Act: -0.1700
Data Index: 7499253 (Open Web Text)
Max Activating Token Index: 97
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.4424. Min Range: -2.4424
Max Act: 2.1794. Min Act: -0.1700
Data Index: 3108003 (Open Web Text)
Max Activating Token Index: 276
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.4424. Min Range: -2.4424
Max Act: 2.1627. Min Act: -0.1700
Data Index: 4041255 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.4424. Min Range: -2.4424
Max Act: 2.1627. Min Act: -0.1700
Data Index: 5534418 (Open Web Text)
Max Activating Token Index: 89
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.4424. Min Range: -2.4424
Max Act: 2.1627. Min Act: -0.1700
Data Index: 6888096 (Open Web Text)
Max Activating Token Index: 655
Click toggle to see full text
Truncated
Full Text #19