Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3460 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.7756. Min Range: -4.7756
Max Act: 4.7756. Min Act: -0.1700
Data Index: 8660267 (Open Web Text)
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.7756. Min Range: -4.7756
Max Act: 4.3068. Min Act: -0.1700
Data Index: 1442213 (Open Web Text)
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.7756. Min Range: -4.7756
Max Act: 4.1818. Min Act: -0.1700
Data Index: 3131384 (Open Web Text)
Max Activating Token Index: 190
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.7756. Min Range: -4.7756
Max Act: 4.1818. Min Act: -0.1700
Data Index: 53822 (Open Web Text)
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.7756. Min Range: -4.7756
Max Act: 4.1505. Min Act: -0.1700
Data Index: 6779137 (Open Web Text)
Max Activating Token Index: 543
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.7756. Min Range: -4.7756
Max Act: 4.1505. Min Act: -0.1700
Data Index: 907659 (Open Web Text)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.7756. Min Range: -4.7756
Max Act: 4.1193. Min Act: -0.1700
Data Index: 7959484 (Open Web Text)
Max Activating Token Index: 61
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.7756. Min Range: -4.7756
Max Act: 4.0568. Min Act: -0.1700
Data Index: 8655556 (Open Web Text)
Max Activating Token Index: 669
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.7756. Min Range: -4.7756
Max Act: 3.9943. Min Act: -0.1700
Data Index: 2293860 (Open Web Text)
Max Activating Token Index: 676
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.7756. Min Range: -4.7756
Max Act: 4.0568. Min Act: -0.1700
Data Index: 247582 (Open Web Text)
Max Activating Token Index: 955
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.7756. Min Range: -4.7756
Max Act: 4.0255. Min Act: -0.1700
Data Index: 578430 (Open Web Text)
Max Activating Token Index: 894
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.7756. Min Range: -4.7756
Max Act: 4.0880. Min Act: -0.1700
Data Index: 1559936 (Open Web Text)
Max Activating Token Index: 799
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.7756. Min Range: -4.7756
Max Act: 4.0880. Min Act: -0.1700
Data Index: 1193095 (Open Web Text)
Max Activating Token Index: 188
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.7756. Min Range: -4.7756
Max Act: 4.0255. Min Act: -0.1700
Data Index: 2238809 (Open Web Text)
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.7756. Min Range: -4.7756
Max Act: 4.0255. Min Act: -0.1700
Data Index: 7283302 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.7756. Min Range: -4.7756
Max Act: 3.9943. Min Act: -0.1700
Data Index: 2128099 (Open Web Text)
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.7756. Min Range: -4.7756
Max Act: 3.9630. Min Act: -0.1700
Data Index: 4064545 (Open Web Text)
Max Activating Token Index: 512
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.7756. Min Range: -4.7756
Max Act: 3.9317. Min Act: -0.1700
Data Index: 1265932 (Open Web Text)
Max Activating Token Index: 927
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.7756. Min Range: -4.7756
Max Act: 3.9943. Min Act: -0.1700
Data Index: 5304593 (Open Web Text)
Max Activating Token Index: 955
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.7756. Min Range: -4.7756
Max Act: 3.9943. Min Act: -0.1700
Data Index: 923023 (Open Web Text)
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #19