Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 991 in Layer 44
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.2256. Min Range: -7.2256
Max Act: 7.2256. Min Act: -0.1700
Data Index: 7617373 (Open Web Text)
Max Activating Token Index: 971
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.2256. Min Range: -7.2256
Max Act: 7.1943. Min Act: -0.1700
Data Index: 6955648 (Open Web Text)
Max Activating Token Index: 424
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.2256. Min Range: -7.2256
Max Act: 7.1943. Min Act: -0.1700
Data Index: 2252213 (Open Web Text)
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.2256. Min Range: -7.2256
Max Act: 7.1631. Min Act: -0.1700
Data Index: 3759671 (Open Web Text)
Max Activating Token Index: 305
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.2256. Min Range: -7.2256
Max Act: 7.0381. Min Act: -0.1700
Data Index: 702371 (Open Web Text)
Max Activating Token Index: 315
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.2256. Min Range: -7.2256
Max Act: 7.0381. Min Act: -0.1700
Data Index: 114603 (Open Web Text)
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.2256. Min Range: -7.2256
Max Act: 7.0068. Min Act: -0.1700
Data Index: 2070472 (Open Web Text)
Max Activating Token Index: 418
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.2256. Min Range: -7.2256
Max Act: 7.0068. Min Act: -0.1700
Data Index: 3241038 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.2256. Min Range: -7.2256
Max Act: 7.0068. Min Act: -0.1700
Data Index: 2723799 (Open Web Text)
Max Activating Token Index: 885
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.2256. Min Range: -7.2256
Max Act: 6.9756. Min Act: -0.1700
Data Index: 5600964 (Open Web Text)
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.2256. Min Range: -7.2256
Max Act: 6.9131. Min Act: -0.1700
Data Index: 942564 (Open Web Text)
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.2256. Min Range: -7.2256
Max Act: 6.9131. Min Act: -0.1700
Data Index: 6716046 (Open Web Text)
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.2256. Min Range: -7.2256
Max Act: 6.9131. Min Act: -0.1700
Data Index: 1393989 (Open Web Text)
Max Activating Token Index: 661
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.2256. Min Range: -7.2256
Max Act: 6.9131. Min Act: -0.1700
Data Index: 4107876 (Open Web Text)
Max Activating Token Index: 400
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.2256. Min Range: -7.2256
Max Act: 6.8818. Min Act: -0.1700
Data Index: 1802344 (Open Web Text)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.2256. Min Range: -7.2256
Max Act: 6.8818. Min Act: -0.1700
Data Index: 7663928 (Open Web Text)
Max Activating Token Index: 837
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.2256. Min Range: -7.2256
Max Act: 6.8818. Min Act: -0.1700
Data Index: 1165005 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.2256. Min Range: -7.2256
Max Act: 6.8506. Min Act: -0.1700
Data Index: 13107 (Open Web Text)
Max Activating Token Index: 714
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.2256. Min Range: -7.2256
Max Act: 6.8506. Min Act: -0.1700
Data Index: 6808868 (Open Web Text)
Max Activating Token Index: 513
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.2256. Min Range: -7.2256
Max Act: 6.8506. Min Act: -0.1700
Data Index: 1335247 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #19