Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4242 in Layer 19
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.0993. Min Range: -4.0993
Max Act: 4.0681. Min Act: -0.1700
Data Index: 4960535 (Open Web Text)
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.0993. Min Range: -4.0993
Max Act: 4.0993. Min Act: -0.1700
Data Index: 1671405 (Open Web Text)
Max Activating Token Index: 549
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.0993. Min Range: -4.0993
Max Act: 4.0368. Min Act: -0.1700
Data Index: 3116976 (Open Web Text)
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.0993. Min Range: -4.0993
Max Act: 4.0056. Min Act: -0.1700
Data Index: 868189 (Open Web Text)
Max Activating Token Index: 568
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.0993. Min Range: -4.0993
Max Act: 4.0368. Min Act: -0.1700
Data Index: 373220 (Open Web Text)
Max Activating Token Index: 529
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.0993. Min Range: -4.0993
Max Act: 4.0056. Min Act: -0.1700
Data Index: 3833498 (Open Web Text)
Max Activating Token Index: 926
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.0993. Min Range: -4.0993
Max Act: 4.0056. Min Act: -0.1700
Data Index: 1253394 (Open Web Text)
Max Activating Token Index: 518
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.0993. Min Range: -4.0993
Max Act: 3.9118. Min Act: -0.1700
Data Index: 7227063 (Open Web Text)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.0993. Min Range: -4.0993
Max Act: 3.9118. Min Act: -0.1700
Data Index: 3820842 (Open Web Text)
Max Activating Token Index: 30
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.0993. Min Range: -4.0993
Max Act: 3.9118. Min Act: -0.1700
Data Index: 3719378 (Open Web Text)
Max Activating Token Index: 981
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.0993. Min Range: -4.0993
Max Act: 3.9118. Min Act: -0.1700
Data Index: 8819962 (Open Web Text)
Max Activating Token Index: 268
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.0993. Min Range: -4.0993
Max Act: 3.9430. Min Act: -0.1700
Data Index: 1742990 (Open Web Text)
Max Activating Token Index: 221
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.0993. Min Range: -4.0993
Max Act: 3.9118. Min Act: -0.1700
Data Index: 320671 (Open Web Text)
Max Activating Token Index: 518
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.0993. Min Range: -4.0993
Max Act: 3.8492. Min Act: -0.1700
Data Index: 891565 (Open Web Text)
Max Activating Token Index: 79
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.0993. Min Range: -4.0993
Max Act: 3.8649. Min Act: -0.1700
Data Index: 3311920 (Open Web Text)
Max Activating Token Index: 257
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.0993. Min Range: -4.0993
Max Act: 3.8649. Min Act: -0.1700
Data Index: 313386 (Open Web Text)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.0993. Min Range: -4.0993
Max Act: 3.8649. Min Act: -0.1700
Data Index: 2811654 (Open Web Text)
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.0993. Min Range: -4.0993
Max Act: 3.8492. Min Act: -0.1700
Data Index: 5117104 (Open Web Text)
Max Activating Token Index: 111
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.0993. Min Range: -4.0993
Max Act: 3.8492. Min Act: -0.1700
Data Index: 7425276 (Open Web Text)
Max Activating Token Index: 889
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.0993. Min Range: -4.0993
Max Act: 3.8336. Min Act: -0.1700
Data Index: 1402015 (Open Web Text)
Max Activating Token Index: 803
Click toggle to see full text
Truncated
Full Text #19