Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1670 in Layer 47
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.8926. Min Range: -7.8926
Max Act: 7.8614. Min Act: -0.1700
Data Index: 1007001 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.8926. Min Range: -7.8926
Max Act: 7.8926. Min Act: -0.1700
Data Index: 8128605 (Open Web Text)
Max Activating Token Index: 271
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.8926. Min Range: -7.8926
Max Act: 7.7989. Min Act: -0.1700
Data Index: 1816027 (Open Web Text)
Max Activating Token Index: 1019
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.8926. Min Range: -7.8926
Max Act: 7.7364. Min Act: -0.1700
Data Index: 8545760 (Open Web Text)
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.8926. Min Range: -7.8926
Max Act: 7.7051. Min Act: -0.1700
Data Index: 8103975 (Open Web Text)
Max Activating Token Index: 195
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.8926. Min Range: -7.8926
Max Act: 7.7051. Min Act: -0.1700
Data Index: 1460706 (Open Web Text)
Max Activating Token Index: 264
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.8926. Min Range: -7.8926
Max Act: 7.6426. Min Act: -0.1700
Data Index: 2431612 (Open Web Text)
Max Activating Token Index: 585
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.8926. Min Range: -7.8926
Max Act: 7.6114. Min Act: -0.1700
Data Index: 8239226 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.8926. Min Range: -7.8926
Max Act: 7.5801. Min Act: -0.1700
Data Index: 8623165 (Open Web Text)
Max Activating Token Index: 178
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.8926. Min Range: -7.8926
Max Act: 7.5801. Min Act: -0.1700
Data Index: 6755224 (Open Web Text)
Max Activating Token Index: 435
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.8926. Min Range: -7.8926
Max Act: 7.5489. Min Act: -0.1700
Data Index: 466159 (Open Web Text)
Max Activating Token Index: 530
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.8926. Min Range: -7.8926
Max Act: 7.5489. Min Act: -0.1700
Data Index: 8359642 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.8926. Min Range: -7.8926
Max Act: 7.5489. Min Act: -0.1700
Data Index: 3215912 (Open Web Text)
Max Activating Token Index: 948
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.8926. Min Range: -7.8926
Max Act: 7.5176. Min Act: -0.1700
Data Index: 895361 (Open Web Text)
Max Activating Token Index: 662
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.8926. Min Range: -7.8926
Max Act: 7.4864. Min Act: -0.1700
Data Index: 142 (Open Web Text)
Max Activating Token Index: 109
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.8926. Min Range: -7.8926
Max Act: 7.4864. Min Act: -0.1700
Data Index: 1350646 (Open Web Text)
Max Activating Token Index: 253
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.8926. Min Range: -7.8926
Max Act: 7.4551. Min Act: -0.1700
Data Index: 3756905 (Open Web Text)
Max Activating Token Index: 73
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.8926. Min Range: -7.8926
Max Act: 7.4551. Min Act: -0.1700
Data Index: 5284177 (Open Web Text)
Max Activating Token Index: 142
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.8926. Min Range: -7.8926
Max Act: 7.4239. Min Act: -0.1700
Data Index: 1005000 (Open Web Text)
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.8926. Min Range: -7.8926
Max Act: 7.4551. Min Act: -0.1700
Data Index: 3720057 (Open Web Text)
Max Activating Token Index: 274
Click toggle to see full text
Truncated
Full Text #19