Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2708 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.2309. Min Range: -7.2309
Max Act: 7.2309. Min Act: -0.1700
Data Index: 3989045 (Open Web Text)
Max Activating Token Index: 782
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.2309. Min Range: -7.2309
Max Act: 7.1684. Min Act: -0.1700
Data Index: 8671991 (Open Web Text)
Max Activating Token Index: 358
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.2309. Min Range: -7.2309
Max Act: 7.1059. Min Act: -0.1700
Data Index: 3744376 (Open Web Text)
Max Activating Token Index: 640
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.2309. Min Range: -7.2309
Max Act: 7.0746. Min Act: -0.1700
Data Index: 425789 (Open Web Text)
Max Activating Token Index: 331
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.2309. Min Range: -7.2309
Max Act: 7.0746. Min Act: -0.1700
Data Index: 5076977 (Open Web Text)
Max Activating Token Index: 964
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.2309. Min Range: -7.2309
Max Act: 6.8871. Min Act: -0.1700
Data Index: 5127132 (Open Web Text)
Max Activating Token Index: 290
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.2309. Min Range: -7.2309
Max Act: 6.8871. Min Act: -0.1700
Data Index: 1250772 (Open Web Text)
Max Activating Token Index: 637
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.2309. Min Range: -7.2309
Max Act: 6.8559. Min Act: -0.1700
Data Index: 4074644 (Open Web Text)
Max Activating Token Index: 759
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.2309. Min Range: -7.2309
Max Act: 6.8559. Min Act: -0.1700
Data Index: 5962497 (Open Web Text)
Max Activating Token Index: 786
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.2309. Min Range: -7.2309
Max Act: 6.8246. Min Act: -0.1700
Data Index: 7946050 (Open Web Text)
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.2309. Min Range: -7.2309
Max Act: 6.8559. Min Act: -0.1700
Data Index: 3656372 (Open Web Text)
Max Activating Token Index: 960
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.2309. Min Range: -7.2309
Max Act: 6.7934. Min Act: -0.1700
Data Index: 2070571 (Open Web Text)
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.2309. Min Range: -7.2309
Max Act: 6.7934. Min Act: -0.1700
Data Index: 884795 (Open Web Text)
Max Activating Token Index: 797
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.2309. Min Range: -7.2309
Max Act: 6.7934. Min Act: -0.1700
Data Index: 788261 (Open Web Text)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.2309. Min Range: -7.2309
Max Act: 6.8246. Min Act: -0.1700
Data Index: 5696045 (Open Web Text)
Max Activating Token Index: 992
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.2309. Min Range: -7.2309
Max Act: 6.7934. Min Act: -0.1700
Data Index: 3287254 (Open Web Text)
Max Activating Token Index: 581
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.2309. Min Range: -7.2309
Max Act: 6.7934. Min Act: -0.1700
Data Index: 7401195 (Open Web Text)
Max Activating Token Index: 165
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.2309. Min Range: -7.2309
Max Act: 6.7309. Min Act: -0.1700
Data Index: 938974 (Open Web Text)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.2309. Min Range: -7.2309
Max Act: 6.7309. Min Act: -0.1700
Data Index: 8486902 (Open Web Text)
Max Activating Token Index: 749
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.2309. Min Range: -7.2309
Max Act: 6.7309. Min Act: -0.1700
Data Index: 7338971 (Open Web Text)
Max Activating Token Index: 875
Click toggle to see full text
Truncated
Full Text #19