Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1419 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.0890. Min Range: -6.0890
Max Act: 6.0890. Min Act: -0.1700
Data Index: 5518344 (Open Web Text)
Max Activating Token Index: 190
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0890. Min Range: -6.0890
Max Act: 5.9953. Min Act: -0.1700
Data Index: 4292027 (Open Web Text)
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0890. Min Range: -6.0890
Max Act: 5.9953. Min Act: -0.1700
Data Index: 4337656 (Open Web Text)
Max Activating Token Index: 285
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0890. Min Range: -6.0890
Max Act: 5.8703. Min Act: -0.1700
Data Index: 3821442 (Open Web Text)
Max Activating Token Index: 930
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0890. Min Range: -6.0890
Max Act: 5.8703. Min Act: -0.1700
Data Index: 423322 (Open Web Text)
Max Activating Token Index: 611
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0890. Min Range: -6.0890
Max Act: 5.8390. Min Act: -0.1700
Data Index: 8238229 (Open Web Text)
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0890. Min Range: -6.0890
Max Act: 5.8078. Min Act: -0.1700
Data Index: 6751932 (Open Web Text)
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0890. Min Range: -6.0890
Max Act: 5.8078. Min Act: -0.1700
Data Index: 7615357 (Open Web Text)
Max Activating Token Index: 276
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0890. Min Range: -6.0890
Max Act: 5.7765. Min Act: -0.1700
Data Index: 3238936 (Open Web Text)
Max Activating Token Index: 610
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0890. Min Range: -6.0890
Max Act: 5.7765. Min Act: -0.1700
Data Index: 4495389 (Open Web Text)
Max Activating Token Index: 714
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0890. Min Range: -6.0890
Max Act: 5.7453. Min Act: -0.1700
Data Index: 2131146 (Open Web Text)
Max Activating Token Index: 377
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0890. Min Range: -6.0890
Max Act: 5.6828. Min Act: -0.1700
Data Index: 160853 (Open Web Text)
Max Activating Token Index: 90
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0890. Min Range: -6.0890
Max Act: 5.7140. Min Act: -0.1700
Data Index: 3558328 (Open Web Text)
Max Activating Token Index: 84
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0890. Min Range: -6.0890
Max Act: 5.6828. Min Act: -0.1700
Data Index: 5320387 (Open Web Text)
Max Activating Token Index: 706
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0890. Min Range: -6.0890
Max Act: 5.6828. Min Act: -0.1700
Data Index: 8769225 (Open Web Text)
Max Activating Token Index: 139
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0890. Min Range: -6.0890
Max Act: 5.6515. Min Act: -0.1700
Data Index: 3803161 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0890. Min Range: -6.0890
Max Act: 5.6828. Min Act: -0.1700
Data Index: 1446973 (Open Web Text)
Max Activating Token Index: 114
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0890. Min Range: -6.0890
Max Act: 5.6515. Min Act: -0.1700
Data Index: 8359688 (Open Web Text)
Max Activating Token Index: 213
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0890. Min Range: -6.0890
Max Act: 5.6515. Min Act: -0.1700
Data Index: 6846647 (Open Web Text)
Max Activating Token Index: 56
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0890. Min Range: -6.0890
Max Act: 5.6515. Min Act: -0.1700
Data Index: 3880438 (Open Web Text)
Max Activating Token Index: 875
Click toggle to see full text
Truncated
Full Text #19