Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1206 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.1149. Min Range: -5.1149
Max Act: 5.1149. Min Act: -0.1700
Data Index: 1709440 (Open Web Text)
Max Activating Token Index: 1017
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.1149. Min Range: -5.1149
Max Act: 4.9587. Min Act: -0.1700
Data Index: 59143 (Open Web Text)
Max Activating Token Index: 89
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.1149. Min Range: -5.1149
Max Act: 4.9274. Min Act: -0.1700
Data Index: 7689296 (Open Web Text)
Max Activating Token Index: 496
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.1149. Min Range: -5.1149
Max Act: 4.9274. Min Act: -0.1700
Data Index: 1230627 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.1149. Min Range: -5.1149
Max Act: 4.9587. Min Act: -0.1700
Data Index: 6038266 (Open Web Text)
Max Activating Token Index: 365
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.1149. Min Range: -5.1149
Max Act: 4.8962. Min Act: -0.1700
Data Index: 8139491 (Open Web Text)
Max Activating Token Index: 637
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.1149. Min Range: -5.1149
Max Act: 4.8962. Min Act: -0.1700
Data Index: 4936724 (Open Web Text)
Max Activating Token Index: 127
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.1149. Min Range: -5.1149
Max Act: 4.8962. Min Act: -0.1700
Data Index: 917082 (Open Web Text)
Max Activating Token Index: 880
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.1149. Min Range: -5.1149
Max Act: 4.8962. Min Act: -0.1700
Data Index: 1466888 (Open Web Text)
Max Activating Token Index: 782
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.1149. Min Range: -5.1149
Max Act: 4.8649. Min Act: -0.1700
Data Index: 5597094 (Open Web Text)
Max Activating Token Index: 689
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.1149. Min Range: -5.1149
Max Act: 4.8649. Min Act: -0.1700
Data Index: 1528726 (Open Web Text)
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.1149. Min Range: -5.1149
Max Act: 4.8649. Min Act: -0.1700
Data Index: 2836110 (Open Web Text)
Max Activating Token Index: 169
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.1149. Min Range: -5.1149
Max Act: 4.8962. Min Act: -0.1700
Data Index: 2138557 (Open Web Text)
Max Activating Token Index: 118
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.1149. Min Range: -5.1149
Max Act: 4.8649. Min Act: -0.1700
Data Index: 8631424 (Open Web Text)
Max Activating Token Index: 556
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.1149. Min Range: -5.1149
Max Act: 4.8337. Min Act: -0.1700
Data Index: 4657592 (Open Web Text)
Max Activating Token Index: 440
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.1149. Min Range: -5.1149
Max Act: 4.8337. Min Act: -0.1700
Data Index: 6057021 (Open Web Text)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.1149. Min Range: -5.1149
Max Act: 4.8337. Min Act: -0.1700
Data Index: 1894252 (Open Web Text)
Max Activating Token Index: 938
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.1149. Min Range: -5.1149
Max Act: 4.8024. Min Act: -0.1700
Data Index: 4787121 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.1149. Min Range: -5.1149
Max Act: 4.8024. Min Act: -0.1700
Data Index: 7017233 (Open Web Text)
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.1149. Min Range: -5.1149
Max Act: 4.8024. Min Act: -0.1700
Data Index: 1574425 (Open Web Text)
Max Activating Token Index: 222
Click toggle to see full text
Truncated
Full Text #19