Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2825 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 8.2355. Min Range: -8.2355
Max Act: 8.2355. Min Act: -0.1700
Data Index: 6753783 (Open Web Text)
Max Activating Token Index: 649
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.2355. Min Range: -8.2355
Max Act: 8.1730. Min Act: -0.1700
Data Index: 7298710 (Open Web Text)
Max Activating Token Index: 811
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.2355. Min Range: -8.2355
Max Act: 8.1105. Min Act: -0.1700
Data Index: 7092918 (Open Web Text)
Max Activating Token Index: 967
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.2355. Min Range: -8.2355
Max Act: 8.1730. Min Act: -0.1700
Data Index: 6265787 (Open Web Text)
Max Activating Token Index: 878
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.2355. Min Range: -8.2355
Max Act: 8.1105. Min Act: -0.1700
Data Index: 1791832 (Open Web Text)
Max Activating Token Index: 797
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.2355. Min Range: -8.2355
Max Act: 8.1105. Min Act: -0.1700
Data Index: 1934515 (Open Web Text)
Max Activating Token Index: 906
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.2355. Min Range: -8.2355
Max Act: 8.0480. Min Act: -0.1700
Data Index: 8732698 (Open Web Text)
Max Activating Token Index: 823
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.2355. Min Range: -8.2355
Max Act: 8.0480. Min Act: -0.1700
Data Index: 6296289 (Open Web Text)
Max Activating Token Index: 887
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.2355. Min Range: -8.2355
Max Act: 8.0480. Min Act: -0.1700
Data Index: 5446427 (Open Web Text)
Max Activating Token Index: 848
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.2355. Min Range: -8.2355
Max Act: 8.0480. Min Act: -0.1700
Data Index: 4696923 (Open Web Text)
Max Activating Token Index: 227
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.2355. Min Range: -8.2355
Max Act: 7.9855. Min Act: -0.1700
Data Index: 257924 (Open Web Text)
Max Activating Token Index: 985
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.2355. Min Range: -8.2355
Max Act: 8.1105. Min Act: -0.1700
Data Index: 7915783 (Open Web Text)
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.2355. Min Range: -8.2355
Max Act: 8.0167. Min Act: -0.1700
Data Index: 5935420 (Open Web Text)
Max Activating Token Index: 759
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.2355. Min Range: -8.2355
Max Act: 7.9855. Min Act: -0.1700
Data Index: 6495499 (Open Web Text)
Max Activating Token Index: 81
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.2355. Min Range: -8.2355
Max Act: 7.9542. Min Act: -0.1700
Data Index: 4383092 (Open Web Text)
Max Activating Token Index: 697
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.2355. Min Range: -8.2355
Max Act: 7.9542. Min Act: -0.1700
Data Index: 1757465 (Open Web Text)
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.2355. Min Range: -8.2355
Max Act: 7.9855. Min Act: -0.1700
Data Index: 3035075 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.2355. Min Range: -8.2355
Max Act: 8.0167. Min Act: -0.1700
Data Index: 1499002 (Open Web Text)
Max Activating Token Index: 982
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.2355. Min Range: -8.2355
Max Act: 7.8605. Min Act: -0.1700
Data Index: 5575979 (Open Web Text)
Max Activating Token Index: 84
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.2355. Min Range: -8.2355
Max Act: 7.8917. Min Act: -0.1700
Data Index: 3974161 (Open Web Text)
Max Activating Token Index: 968
Click toggle to see full text
Truncated
Full Text #19