Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4077 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.2765. Min Range: -6.2765
Max Act: 6.2765. Min Act: -0.1700
Data Index: 1159051 (Open Web Text)
Max Activating Token Index: 986
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.2765. Min Range: -6.2765
Max Act: 5.9015. Min Act: -0.1700
Data Index: 3043490 (Open Web Text)
Max Activating Token Index: 872
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.2765. Min Range: -6.2765
Max Act: 5.8390. Min Act: -0.1700
Data Index: 4939923 (Open Web Text)
Max Activating Token Index: 66
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.2765. Min Range: -6.2765
Max Act: 5.7765. Min Act: -0.1700
Data Index: 4595451 (Open Web Text)
Max Activating Token Index: 820
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.2765. Min Range: -6.2765
Max Act: 5.7765. Min Act: -0.1700
Data Index: 731663 (Open Web Text)
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.2765. Min Range: -6.2765
Max Act: 5.7453. Min Act: -0.1700
Data Index: 2150589 (Open Web Text)
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.2765. Min Range: -6.2765
Max Act: 5.7140. Min Act: -0.1700
Data Index: 2898738 (Open Web Text)
Max Activating Token Index: 659
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.2765. Min Range: -6.2765
Max Act: 5.7140. Min Act: -0.1700
Data Index: 2812872 (Open Web Text)
Max Activating Token Index: 464
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.2765. Min Range: -6.2765
Max Act: 5.7140. Min Act: -0.1700
Data Index: 5271865 (Open Web Text)
Max Activating Token Index: 657
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.2765. Min Range: -6.2765
Max Act: 5.7140. Min Act: -0.1700
Data Index: 3458608 (Open Web Text)
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.2765. Min Range: -6.2765
Max Act: 5.6828. Min Act: -0.1700
Data Index: 490708 (Open Web Text)
Max Activating Token Index: 958
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.2765. Min Range: -6.2765
Max Act: 5.6828. Min Act: -0.1700
Data Index: 5283979 (Open Web Text)
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.2765. Min Range: -6.2765
Max Act: 5.6828. Min Act: -0.1700
Data Index: 7639833 (Open Web Text)
Max Activating Token Index: 296
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.2765. Min Range: -6.2765
Max Act: 5.6515. Min Act: -0.1700
Data Index: 8047659 (Open Web Text)
Max Activating Token Index: 202
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.2765. Min Range: -6.2765
Max Act: 5.6515. Min Act: -0.1700
Data Index: 7213553 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.2765. Min Range: -6.2765
Max Act: 5.6828. Min Act: -0.1700
Data Index: 8810555 (Open Web Text)
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.2765. Min Range: -6.2765
Max Act: 5.5890. Min Act: -0.1700
Data Index: 5811705 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.2765. Min Range: -6.2765
Max Act: 5.6203. Min Act: -0.1700
Data Index: 1384707 (Open Web Text)
Max Activating Token Index: 960
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.2765. Min Range: -6.2765
Max Act: 5.6515. Min Act: -0.1700
Data Index: 6671819 (Open Web Text)
Max Activating Token Index: 969
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.2765. Min Range: -6.2765
Max Act: 5.5890. Min Act: -0.1700
Data Index: 163909 (Open Web Text)
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #19