Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2985 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.7756. Min Range: -6.7756
Max Act: 6.7756. Min Act: -0.1700
Data Index: 8806796 (Open Web Text)
Max Activating Token Index: 625
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.7756. Min Range: -6.7756
Max Act: 6.6506. Min Act: -0.1700
Data Index: 7706351 (Open Web Text)
Max Activating Token Index: 786
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.7756. Min Range: -6.7756
Max Act: 6.5256. Min Act: -0.1700
Data Index: 7431095 (Open Web Text)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.7756. Min Range: -6.7756
Max Act: 6.4943. Min Act: -0.1700
Data Index: 1593705 (Open Web Text)
Max Activating Token Index: 944
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.7756. Min Range: -6.7756
Max Act: 6.4318. Min Act: -0.1700
Data Index: 4326611 (Open Web Text)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.7756. Min Range: -6.7756
Max Act: 6.4318. Min Act: -0.1700
Data Index: 5717946 (Open Web Text)
Max Activating Token Index: 161
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.7756. Min Range: -6.7756
Max Act: 6.4318. Min Act: -0.1700
Data Index: 847968 (Open Web Text)
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.7756. Min Range: -6.7756
Max Act: 6.4318. Min Act: -0.1700
Data Index: 7692118 (Open Web Text)
Max Activating Token Index: 751
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.7756. Min Range: -6.7756
Max Act: 6.4318. Min Act: -0.1700
Data Index: 3293579 (Open Web Text)
Max Activating Token Index: 975
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.7756. Min Range: -6.7756
Max Act: 6.4318. Min Act: -0.1700
Data Index: 8063597 (Open Web Text)
Max Activating Token Index: 739
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.7756. Min Range: -6.7756
Max Act: 6.4006. Min Act: -0.1700
Data Index: 6061029 (Open Web Text)
Max Activating Token Index: 853
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.7756. Min Range: -6.7756
Max Act: 6.3693. Min Act: -0.1700
Data Index: 4804802 (Open Web Text)
Max Activating Token Index: 524
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.7756. Min Range: -6.7756
Max Act: 6.3381. Min Act: -0.1700
Data Index: 3336203 (Open Web Text)
Max Activating Token Index: 705
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.7756. Min Range: -6.7756
Max Act: 6.3381. Min Act: -0.1700
Data Index: 268184 (Open Web Text)
Max Activating Token Index: 899
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.7756. Min Range: -6.7756
Max Act: 6.3068. Min Act: -0.1700
Data Index: 2680528 (Open Web Text)
Max Activating Token Index: 1011
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.7756. Min Range: -6.7756
Max Act: 6.3068. Min Act: -0.1700
Data Index: 7380259 (Open Web Text)
Max Activating Token Index: 724
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.7756. Min Range: -6.7756
Max Act: 6.3068. Min Act: -0.1700
Data Index: 2061413 (Open Web Text)
Max Activating Token Index: 93
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.7756. Min Range: -6.7756
Max Act: 6.2756. Min Act: -0.1700
Data Index: 2815286 (Open Web Text)
Max Activating Token Index: 663
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.7756. Min Range: -6.7756
Max Act: 6.2756. Min Act: -0.1700
Data Index: 1192700 (Open Web Text)
Max Activating Token Index: 942
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.7756. Min Range: -6.7756
Max Act: 6.2443. Min Act: -0.1700
Data Index: 6236180 (Open Web Text)
Max Activating Token Index: 971
Click toggle to see full text
Truncated
Full Text #19