Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3943 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.4865. Min Range: -5.4865
Max Act: 5.4865. Min Act: -0.1700
Data Index: 2772004 (Open Web Text)
Max Activating Token Index: 78
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.4865. Min Range: -5.4865
Max Act: 5.4552. Min Act: -0.1700
Data Index: 4883578 (Open Web Text)
Max Activating Token Index: 174
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.4865. Min Range: -5.4865
Max Act: 5.4240. Min Act: -0.1700
Data Index: 1514783 (Open Web Text)
Max Activating Token Index: 99
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.4865. Min Range: -5.4865
Max Act: 5.3615. Min Act: -0.1700
Data Index: 7996048 (Open Web Text)
Max Activating Token Index: 122
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.4865. Min Range: -5.4865
Max Act: 5.3615. Min Act: -0.1700
Data Index: 1403109 (Open Web Text)
Max Activating Token Index: 396
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.4865. Min Range: -5.4865
Max Act: 5.2990. Min Act: -0.1700
Data Index: 6652516 (Open Web Text)
Max Activating Token Index: 905
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.4865. Min Range: -5.4865
Max Act: 5.3302. Min Act: -0.1700
Data Index: 3807866 (Open Web Text)
Max Activating Token Index: 919
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.4865. Min Range: -5.4865
Max Act: 5.2990. Min Act: -0.1700
Data Index: 6856432 (Open Web Text)
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.4865. Min Range: -5.4865
Max Act: 5.2990. Min Act: -0.1700
Data Index: 2043395 (Open Web Text)
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.4865. Min Range: -5.4865
Max Act: 5.2990. Min Act: -0.1700
Data Index: 5110105 (Open Web Text)
Max Activating Token Index: 377
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.4865. Min Range: -5.4865
Max Act: 5.2990. Min Act: -0.1700
Data Index: 4332834 (Open Web Text)
Max Activating Token Index: 653
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.4865. Min Range: -5.4865
Max Act: 5.2677. Min Act: -0.1700
Data Index: 641872 (Open Web Text)
Max Activating Token Index: 315
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.4865. Min Range: -5.4865
Max Act: 5.2677. Min Act: -0.1700
Data Index: 5470847 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.4865. Min Range: -5.4865
Max Act: 5.2677. Min Act: -0.1700
Data Index: 614585 (Open Web Text)
Max Activating Token Index: 955
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.4865. Min Range: -5.4865
Max Act: 5.2677. Min Act: -0.1700
Data Index: 7323154 (Open Web Text)
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.4865. Min Range: -5.4865
Max Act: 5.2677. Min Act: -0.1700
Data Index: 2836875 (Open Web Text)
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.4865. Min Range: -5.4865
Max Act: 5.2365. Min Act: -0.1700
Data Index: 2892373 (Open Web Text)
Max Activating Token Index: 878
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.4865. Min Range: -5.4865
Max Act: 5.2677. Min Act: -0.1700
Data Index: 2278016 (Open Web Text)
Max Activating Token Index: 779
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.4865. Min Range: -5.4865
Max Act: 5.2365. Min Act: -0.1700
Data Index: 5626894 (Open Web Text)
Max Activating Token Index: 381
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.4865. Min Range: -5.4865
Max Act: 5.2365. Min Act: -0.1700
Data Index: 3569784 (Open Web Text)
Max Activating Token Index: 811
Click toggle to see full text
Truncated
Full Text #19