Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5190 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 1.0972. Min Range: -1.0972
Max Act: 1.0972. Min Act: -0.1700
Data Index: 2467625 (Open Web Text)
Max Activating Token Index: 1020
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.0972. Min Range: -1.0972
Max Act: 1.0535. Min Act: -0.1700
Data Index: 299731 (Open Web Text)
Max Activating Token Index: 1022
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.0972. Min Range: -1.0972
Max Act: 1.0274. Min Act: -0.1700
Data Index: 4031942 (Open Web Text)
Max Activating Token Index: 1021
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.0972. Min Range: -1.0972
Max Act: 1.0187. Min Act: -0.1700
Data Index: 2053353 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.0972. Min Range: -1.0972
Max Act: 1.0187. Min Act: -0.1700
Data Index: 1327122 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.0972. Min Range: -1.0972
Max Act: 0.9926. Min Act: -0.1700
Data Index: 4648097 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.0972. Min Range: -1.0972
Max Act: 0.9753. Min Act: -0.1700
Data Index: 3608009 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.0972. Min Range: -1.0972
Max Act: 0.9667. Min Act: -0.1697
Data Index: 6432493 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.0972. Min Range: -1.0972
Max Act: 0.9753. Min Act: -0.1700
Data Index: 5137074 (Open Web Text)
Max Activating Token Index: 814
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.0972. Min Range: -1.0972
Max Act: 0.9494. Min Act: -0.1700
Data Index: 2848301 (Open Web Text)
Max Activating Token Index: 821
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.0972. Min Range: -1.0972
Max Act: 0.9494. Min Act: -0.1700
Data Index: 508811 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.0972. Min Range: -1.0972
Max Act: 0.9494. Min Act: -0.1700
Data Index: 2183996 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.0972. Min Range: -1.0972
Max Act: 0.9494. Min Act: -0.1700
Data Index: 1363958 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.0972. Min Range: -1.0972
Max Act: 0.9408. Min Act: -0.1700
Data Index: 4458790 (Open Web Text)
Max Activating Token Index: 821
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.0972. Min Range: -1.0972
Max Act: 0.9408. Min Act: -0.1698
Data Index: 2361212 (Open Web Text)
Max Activating Token Index: 840
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.0972. Min Range: -1.0972
Max Act: 0.9236. Min Act: -0.1700
Data Index: 4761215 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.0972. Min Range: -1.0972
Max Act: 0.9322. Min Act: -0.1700
Data Index: 138877 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.0972. Min Range: -1.0972
Max Act: 0.9408. Min Act: -0.1700
Data Index: 1501158 (Open Web Text)
Max Activating Token Index: 1021
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.0972. Min Range: -1.0972
Max Act: 0.9236. Min Act: -0.1700
Data Index: 3328212 (Open Web Text)
Max Activating Token Index: 1019
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.0972. Min Range: -1.0972
Max Act: 0.9322. Min Act: -0.1700
Data Index: 1524866 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #19