Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4845 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.4250. Min Range: -4.4250
Max Act: 4.4250. Min Act: -0.1700
Data Index: 369799 (Open Web Text)
Max Activating Token Index: 669
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.4250. Min Range: -4.4250
Max Act: 4.4250. Min Act: -0.1700
Data Index: 8372727 (Open Web Text)
Max Activating Token Index: 189
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.4250. Min Range: -4.4250
Max Act: 4.3937. Min Act: -0.1700
Data Index: 7486812 (Open Web Text)
Max Activating Token Index: 118
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.4250. Min Range: -4.4250
Max Act: 4.3625. Min Act: -0.1700
Data Index: 707914 (Open Web Text)
Max Activating Token Index: 726
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.4250. Min Range: -4.4250
Max Act: 4.3625. Min Act: -0.1700
Data Index: 2318828 (Open Web Text)
Max Activating Token Index: 643
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.4250. Min Range: -4.4250
Max Act: 4.3625. Min Act: -0.1700
Data Index: 89291 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.4250. Min Range: -4.4250
Max Act: 4.3625. Min Act: -0.1700
Data Index: 1136022 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.4250. Min Range: -4.4250
Max Act: 4.2687. Min Act: -0.1700
Data Index: 5748954 (Open Web Text)
Max Activating Token Index: 731
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.4250. Min Range: -4.4250
Max Act: 4.2687. Min Act: -0.1700
Data Index: 2637786 (Open Web Text)
Max Activating Token Index: 863
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.4250. Min Range: -4.4250
Max Act: 4.2687. Min Act: -0.1700
Data Index: 1559656 (Open Web Text)
Max Activating Token Index: 116
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.4250. Min Range: -4.4250
Max Act: 4.2687. Min Act: -0.1700
Data Index: 8730579 (Open Web Text)
Max Activating Token Index: 221
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.4250. Min Range: -4.4250
Max Act: 4.2375. Min Act: -0.1700
Data Index: 8183112 (Open Web Text)
Max Activating Token Index: 755
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.4250. Min Range: -4.4250
Max Act: 4.2375. Min Act: -0.1700
Data Index: 3325656 (Open Web Text)
Max Activating Token Index: 107
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.4250. Min Range: -4.4250
Max Act: 4.2375. Min Act: -0.1700
Data Index: 6863909 (Open Web Text)
Max Activating Token Index: 213
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.4250. Min Range: -4.4250
Max Act: 4.2375. Min Act: -0.1700
Data Index: 4329595 (Open Web Text)
Max Activating Token Index: 815
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.4250. Min Range: -4.4250
Max Act: 4.2375. Min Act: -0.1700
Data Index: 7828679 (Open Web Text)
Max Activating Token Index: 720
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.4250. Min Range: -4.4250
Max Act: 4.2062. Min Act: -0.1700
Data Index: 715932 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.4250. Min Range: -4.4250
Max Act: 4.2062. Min Act: -0.1700
Data Index: 7321567 (Open Web Text)
Max Activating Token Index: 549
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.4250. Min Range: -4.4250
Max Act: 4.1750. Min Act: -0.1700
Data Index: 8716768 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.4250. Min Range: -4.4250
Max Act: 4.2062. Min Act: -0.1700
Data Index: 5505330 (Open Web Text)
Max Activating Token Index: 685
Click toggle to see full text
Truncated
Full Text #19