Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 4373 in Layer 17
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 6.9321. Min Range: -6.9321
Max Act: 6.9321. Min Act: -0.1700
Data Index: 2093855 (Open Web Text)
Max Activating Token Index: 634
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.9321. Min Range: -6.9321
Max Act: 6.6821. Min Act: -0.1700
Data Index: 7845221 (Open Web Text)
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.9321. Min Range: -6.9321
Max Act: 6.6196. Min Act: -0.1700
Data Index: 708381 (Open Web Text)
Max Activating Token Index: 818
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.9321. Min Range: -6.9321
Max Act: 6.5571. Min Act: -0.1700
Data Index: 8137029 (Open Web Text)
Max Activating Token Index: 250
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.9321. Min Range: -6.9321
Max Act: 6.5258. Min Act: -0.1700
Data Index: 880832 (Open Web Text)
Max Activating Token Index: 789
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.9321. Min Range: -6.9321
Max Act: 6.4946. Min Act: -0.1700
Data Index: 7974013 (Open Web Text)
Max Activating Token Index: 137
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.9321. Min Range: -6.9321
Max Act: 6.5258. Min Act: -0.1700
Data Index: 7556180 (Open Web Text)
Max Activating Token Index: 837
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.9321. Min Range: -6.9321
Max Act: 6.4321. Min Act: -0.1700
Data Index: 5829555 (Open Web Text)
Max Activating Token Index: 334
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.9321. Min Range: -6.9321
Max Act: 6.4008. Min Act: -0.1700
Data Index: 5751036 (Open Web Text)
Max Activating Token Index: 364
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.9321. Min Range: -6.9321
Max Act: 6.4008. Min Act: -0.1700
Data Index: 5696606 (Open Web Text)
Max Activating Token Index: 389
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.9321. Min Range: -6.9321
Max Act: 6.3696. Min Act: -0.1700
Data Index: 7827482 (Open Web Text)
Max Activating Token Index: 608
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.9321. Min Range: -6.9321
Max Act: 6.4008. Min Act: -0.1700
Data Index: 980732 (Open Web Text)
Max Activating Token Index: 893
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.9321. Min Range: -6.9321
Max Act: 6.3696. Min Act: -0.1700
Data Index: 1344312 (Open Web Text)
Max Activating Token Index: 749
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.9321. Min Range: -6.9321
Max Act: 6.3696. Min Act: -0.1700
Data Index: 8505031 (Open Web Text)
Max Activating Token Index: 784
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.9321. Min Range: -6.9321
Max Act: 6.3383. Min Act: -0.1700
Data Index: 3093969 (Open Web Text)
Max Activating Token Index: 905
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.9321. Min Range: -6.9321
Max Act: 6.3383. Min Act: -0.1700
Data Index: 1242841 (Open Web Text)
Max Activating Token Index: 20
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.9321. Min Range: -6.9321
Max Act: 6.3383. Min Act: -0.1700
Data Index: 4625933 (Open Web Text)
Max Activating Token Index: 368
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.9321. Min Range: -6.9321
Max Act: 6.3071. Min Act: -0.1700
Data Index: 3539465 (Open Web Text)
Max Activating Token Index: 983
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.9321. Min Range: -6.9321
Max Act: 6.2758. Min Act: -0.1700
Data Index: 1034720 (Open Web Text)
Max Activating Token Index: 868
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.9321. Min Range: -6.9321
Max Act: 6.2758. Min Act: -0.1700
Data Index: 2019805 (Open Web Text)
Max Activating Token Index: 801
Click toggle to see full text
Truncated
Full Text #19