Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3096 in Layer 28
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 6.6730. Min Range: -6.6730
Max Act: 6.6730. Min Act: -0.1700
Data Index: 6426610 (Open Web Text)
Max Activating Token Index: 891
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.6730. Min Range: -6.6730
Max Act: 6.4855. Min Act: -0.1700
Data Index: 5565659 (Open Web Text)
Max Activating Token Index: 377
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.6730. Min Range: -6.6730
Max Act: 6.4230. Min Act: -0.1700
Data Index: 4020711 (Open Web Text)
Max Activating Token Index: 530
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.6730. Min Range: -6.6730
Max Act: 6.3917. Min Act: -0.1700
Data Index: 2054626 (Open Web Text)
Max Activating Token Index: 942
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.6730. Min Range: -6.6730
Max Act: 6.3605. Min Act: -0.1700
Data Index: 2114942 (Open Web Text)
Max Activating Token Index: 402
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.6730. Min Range: -6.6730
Max Act: 6.3605. Min Act: -0.1700
Data Index: 8700165 (Open Web Text)
Max Activating Token Index: 895
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.6730. Min Range: -6.6730
Max Act: 6.3292. Min Act: -0.1700
Data Index: 8631560 (Open Web Text)
Max Activating Token Index: 985
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.6730. Min Range: -6.6730
Max Act: 6.3292. Min Act: -0.1700
Data Index: 3548044 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.6730. Min Range: -6.6730
Max Act: 6.3292. Min Act: -0.1700
Data Index: 314732 (Open Web Text)
Max Activating Token Index: 419
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.6730. Min Range: -6.6730
Max Act: 6.2980. Min Act: -0.1700
Data Index: 7303323 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.6730. Min Range: -6.6730
Max Act: 6.2355. Min Act: -0.1700
Data Index: 5180775 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.6730. Min Range: -6.6730
Max Act: 6.2667. Min Act: -0.1700
Data Index: 7698772 (Open Web Text)
Max Activating Token Index: 775
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.6730. Min Range: -6.6730
Max Act: 6.2042. Min Act: -0.1700
Data Index: 2198651 (Open Web Text)
Max Activating Token Index: 37
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.6730. Min Range: -6.6730
Max Act: 6.2355. Min Act: -0.1700
Data Index: 4703360 (Open Web Text)
Max Activating Token Index: 788
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.6730. Min Range: -6.6730
Max Act: 6.1730. Min Act: -0.1700
Data Index: 4015477 (Open Web Text)
Max Activating Token Index: 631
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.6730. Min Range: -6.6730
Max Act: 6.1417. Min Act: -0.1700
Data Index: 4529171 (Open Web Text)
Max Activating Token Index: 867
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.6730. Min Range: -6.6730
Max Act: 6.1417. Min Act: -0.1700
Data Index: 4511231 (Open Web Text)
Max Activating Token Index: 659
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.6730. Min Range: -6.6730
Max Act: 6.1417. Min Act: -0.1700
Data Index: 1196474 (Open Web Text)
Max Activating Token Index: 810
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.6730. Min Range: -6.6730
Max Act: 6.1417. Min Act: -0.1700
Data Index: 2632332 (Open Web Text)
Max Activating Token Index: 402
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.6730. Min Range: -6.6730
Max Act: 6.1417. Min Act: -0.1700
Data Index: 1375054 (Open Web Text)
Max Activating Token Index: 702
Click toggle to see full text
Truncated
Full Text #19