Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3478 in Layer 26
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.0377. Min Range: -5.0377
Max Act: 5.0377. Min Act: -0.1700
Data Index: 816742 (Open Web Text)
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0377. Min Range: -5.0377
Max Act: 5.0377. Min Act: -0.1700
Data Index: 7507421 (Open Web Text)
Max Activating Token Index: 95
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0377. Min Range: -5.0377
Max Act: 5.0064. Min Act: -0.1700
Data Index: 1046349 (Open Web Text)
Max Activating Token Index: 518
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0377. Min Range: -5.0377
Max Act: 5.0064. Min Act: -0.1700
Data Index: 4133933 (Open Web Text)
Max Activating Token Index: 905
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0377. Min Range: -5.0377
Max Act: 4.9752. Min Act: -0.1700
Data Index: 379666 (Open Web Text)
Max Activating Token Index: 1002
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0377. Min Range: -5.0377
Max Act: 4.9752. Min Act: -0.1700
Data Index: 8024167 (Open Web Text)
Max Activating Token Index: 97
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0377. Min Range: -5.0377
Max Act: 4.9439. Min Act: -0.1700
Data Index: 2404904 (Open Web Text)
Max Activating Token Index: 959
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0377. Min Range: -5.0377
Max Act: 4.9439. Min Act: -0.1700
Data Index: 4111577 (Open Web Text)
Max Activating Token Index: 473
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0377. Min Range: -5.0377
Max Act: 4.8814. Min Act: -0.1700
Data Index: 5532926 (Open Web Text)
Max Activating Token Index: 169
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0377. Min Range: -5.0377
Max Act: 4.8814. Min Act: -0.1700
Data Index: 7823473 (Open Web Text)
Max Activating Token Index: 293
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0377. Min Range: -5.0377
Max Act: 4.8814. Min Act: -0.1700
Data Index: 8750789 (Open Web Text)
Max Activating Token Index: 204
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0377. Min Range: -5.0377
Max Act: 4.9127. Min Act: -0.1700
Data Index: 640858 (Open Web Text)
Max Activating Token Index: 72
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0377. Min Range: -5.0377
Max Act: 4.8814. Min Act: -0.1700
Data Index: 186040 (Open Web Text)
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0377. Min Range: -5.0377
Max Act: 4.8502. Min Act: -0.1700
Data Index: 3748948 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0377. Min Range: -5.0377
Max Act: 4.8502. Min Act: -0.1700
Data Index: 6854857 (Open Web Text)
Max Activating Token Index: 551
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0377. Min Range: -5.0377
Max Act: 4.8502. Min Act: -0.1700
Data Index: 6818034 (Open Web Text)
Max Activating Token Index: 252
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0377. Min Range: -5.0377
Max Act: 4.8189. Min Act: -0.1700
Data Index: 8561933 (Open Web Text)
Max Activating Token Index: 357
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0377. Min Range: -5.0377
Max Act: 4.8189. Min Act: -0.1700
Data Index: 1627925 (Open Web Text)
Max Activating Token Index: 50
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0377. Min Range: -5.0377
Max Act: 4.7877. Min Act: -0.1700
Data Index: 4182903 (Open Web Text)
Max Activating Token Index: 343
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0377. Min Range: -5.0377
Max Act: 4.7877. Min Act: -0.1700
Data Index: 301938 (Open Web Text)
Max Activating Token Index: 1020
Click toggle to see full text
Truncated
Full Text #19