Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2634 in Layer 44
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.3868. Min Range: -7.3868
Max Act: 7.3868. Min Act: -0.1700
Data Index: 1616118 (Open Web Text)
Max Activating Token Index: 368
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.3868. Min Range: -7.3868
Max Act: 7.3243. Min Act: -0.1700
Data Index: 5767589 (Open Web Text)
Max Activating Token Index: 982
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.3868. Min Range: -7.3868
Max Act: 7.2618. Min Act: -0.1700
Data Index: 3588340 (Open Web Text)
Max Activating Token Index: 431
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.3868. Min Range: -7.3868
Max Act: 7.1055. Min Act: -0.1700
Data Index: 6502436 (Open Web Text)
Max Activating Token Index: 60
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.3868. Min Range: -7.3868
Max Act: 7.0118. Min Act: -0.1700
Data Index: 1136363 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.3868. Min Range: -7.3868
Max Act: 7.0430. Min Act: -0.1700
Data Index: 49299 (Open Web Text)
Max Activating Token Index: 769
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.3868. Min Range: -7.3868
Max Act: 7.0430. Min Act: -0.1700
Data Index: 4216176 (Open Web Text)
Max Activating Token Index: 782
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.3868. Min Range: -7.3868
Max Act: 7.0118. Min Act: -0.1700
Data Index: 1448559 (Open Web Text)
Max Activating Token Index: 912
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.3868. Min Range: -7.3868
Max Act: 6.9180. Min Act: -0.1700
Data Index: 3538652 (Open Web Text)
Max Activating Token Index: 693
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.3868. Min Range: -7.3868
Max Act: 6.9180. Min Act: -0.1700
Data Index: 6672829 (Open Web Text)
Max Activating Token Index: 299
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.3868. Min Range: -7.3868
Max Act: 6.9493. Min Act: -0.1700
Data Index: 3798045 (Open Web Text)
Max Activating Token Index: 1015
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.3868. Min Range: -7.3868
Max Act: 6.9180. Min Act: -0.1700
Data Index: 264252 (Open Web Text)
Max Activating Token Index: 331
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.3868. Min Range: -7.3868
Max Act: 6.9180. Min Act: -0.1700
Data Index: 7039996 (Open Web Text)
Max Activating Token Index: 931
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.3868. Min Range: -7.3868
Max Act: 6.8243. Min Act: -0.1700
Data Index: 7173137 (Open Web Text)
Max Activating Token Index: 633
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.3868. Min Range: -7.3868
Max Act: 6.8555. Min Act: -0.1700
Data Index: 5511012 (Open Web Text)
Max Activating Token Index: 986
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.3868. Min Range: -7.3868
Max Act: 6.8243. Min Act: -0.1700
Data Index: 2344810 (Open Web Text)
Max Activating Token Index: 943
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.3868. Min Range: -7.3868
Max Act: 6.7930. Min Act: -0.1700
Data Index: 6284419 (Open Web Text)
Max Activating Token Index: 491
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.3868. Min Range: -7.3868
Max Act: 6.7618. Min Act: -0.1700
Data Index: 1141917 (Open Web Text)
Max Activating Token Index: 66
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.3868. Min Range: -7.3868
Max Act: 6.7618. Min Act: -0.1700
Data Index: 4272376 (Open Web Text)
Max Activating Token Index: 918
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.3868. Min Range: -7.3868
Max Act: 6.7618. Min Act: -0.1700
Data Index: 617535 (Open Web Text)
Max Activating Token Index: 1017
Click toggle to see full text
Truncated
Full Text #19