Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2071 in Layer 28
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.3256. Min Range: -5.3256
Max Act: 5.3256. Min Act: -0.1700
Data Index: 7856496 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.3256. Min Range: -5.3256
Max Act: 5.3256. Min Act: -0.1700
Data Index: 3580496 (Open Web Text)
Max Activating Token Index: 635
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.3256. Min Range: -5.3256
Max Act: 5.2943. Min Act: -0.1700
Data Index: 5303643 (Open Web Text)
Max Activating Token Index: 284
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.3256. Min Range: -5.3256
Max Act: 5.2631. Min Act: -0.1700
Data Index: 894039 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.3256. Min Range: -5.3256
Max Act: 5.2943. Min Act: -0.1700
Data Index: 6981988 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.3256. Min Range: -5.3256
Max Act: 5.2943. Min Act: -0.1700
Data Index: 2624731 (Open Web Text)
Max Activating Token Index: 226
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.3256. Min Range: -5.3256
Max Act: 5.2318. Min Act: -0.1700
Data Index: 42833 (Open Web Text)
Max Activating Token Index: 28
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.3256. Min Range: -5.3256
Max Act: 5.2006. Min Act: -0.1700
Data Index: 7856495 (Open Web Text)
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.3256. Min Range: -5.3256
Max Act: 5.2006. Min Act: -0.1700
Data Index: 2021053 (Open Web Text)
Max Activating Token Index: 994
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.3256. Min Range: -5.3256
Max Act: 5.2006. Min Act: -0.1700
Data Index: 5303642 (Open Web Text)
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.3256. Min Range: -5.3256
Max Act: 5.1693. Min Act: -0.1700
Data Index: 1910329 (Open Web Text)
Max Activating Token Index: 207
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.3256. Min Range: -5.3256
Max Act: 5.1693. Min Act: -0.1700
Data Index: 5915540 (Open Web Text)
Max Activating Token Index: 908
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.3256. Min Range: -5.3256
Max Act: 5.1693. Min Act: -0.1700
Data Index: 5426265 (Open Web Text)
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.3256. Min Range: -5.3256
Max Act: 5.1381. Min Act: -0.1700
Data Index: 1219950 (Open Web Text)
Max Activating Token Index: 187
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.3256. Min Range: -5.3256
Max Act: 5.1381. Min Act: -0.1700
Data Index: 894038 (Open Web Text)
Max Activating Token Index: 483
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.3256. Min Range: -5.3256
Max Act: 5.1381. Min Act: -0.1700
Data Index: 1666108 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.3256. Min Range: -5.3256
Max Act: 5.1381. Min Act: -0.1700
Data Index: 2945708 (Open Web Text)
Max Activating Token Index: 304
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.3256. Min Range: -5.3256
Max Act: 5.1381. Min Act: -0.1700
Data Index: 1627859 (Open Web Text)
Max Activating Token Index: 335
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.3256. Min Range: -5.3256
Max Act: 5.1068. Min Act: -0.1700
Data Index: 2541672 (Open Web Text)
Max Activating Token Index: 291
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.3256. Min Range: -5.3256
Max Act: 5.1068. Min Act: -0.1700
Data Index: 6067996 (Open Web Text)
Max Activating Token Index: 655
Click toggle to see full text
Truncated
Full Text #19