Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4024 in Layer 27
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.0366. Min Range: -9.0366
Max Act: 9.0366. Min Act: -0.1700
Data Index: 5635253 (Open Web Text)
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.0366. Min Range: -9.0366
Max Act: 8.6616. Min Act: -0.1700
Data Index: 6108659 (Open Web Text)
Max Activating Token Index: 809
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.0366. Min Range: -9.0366
Max Act: 8.7241. Min Act: -0.1700
Data Index: 7073530 (Open Web Text)
Max Activating Token Index: 219
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.0366. Min Range: -9.0366
Max Act: 8.5366. Min Act: -0.1700
Data Index: 7952904 (Open Web Text)
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.0366. Min Range: -9.0366
Max Act: 8.4116. Min Act: -0.1700
Data Index: 3569112 (Open Web Text)
Max Activating Token Index: 901
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.0366. Min Range: -9.0366
Max Act: 8.4741. Min Act: -0.1700
Data Index: 4319535 (Open Web Text)
Max Activating Token Index: 996
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.0366. Min Range: -9.0366
Max Act: 8.4741. Min Act: -0.1700
Data Index: 4225250 (Open Web Text)
Max Activating Token Index: 235
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.0366. Min Range: -9.0366
Max Act: 8.3491. Min Act: -0.1700
Data Index: 4492552 (Open Web Text)
Max Activating Token Index: 500
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.0366. Min Range: -9.0366
Max Act: 8.4116. Min Act: -0.1700
Data Index: 7840937 (Open Web Text)
Max Activating Token Index: 315
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.0366. Min Range: -9.0366
Max Act: 8.2241. Min Act: -0.1700
Data Index: 2615097 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.0366. Min Range: -9.0366
Max Act: 8.2866. Min Act: -0.1700
Data Index: 1135875 (Open Web Text)
Max Activating Token Index: 780
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.0366. Min Range: -9.0366
Max Act: 8.2241. Min Act: -0.1700
Data Index: 7315523 (Open Web Text)
Max Activating Token Index: 519
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.0366. Min Range: -9.0366
Max Act: 8.2241. Min Act: -0.1700
Data Index: 6146687 (Open Web Text)
Max Activating Token Index: 469
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.0366. Min Range: -9.0366
Max Act: 8.1616. Min Act: -0.1700
Data Index: 8606341 (Open Web Text)
Max Activating Token Index: 688
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.0366. Min Range: -9.0366
Max Act: 8.0991. Min Act: -0.1700
Data Index: 8226715 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.0366. Min Range: -9.0366
Max Act: 8.1616. Min Act: -0.1700
Data Index: 2339011 (Open Web Text)
Max Activating Token Index: 103
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.0366. Min Range: -9.0366
Max Act: 8.1616. Min Act: -0.1700
Data Index: 5914341 (Open Web Text)
Max Activating Token Index: 445
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.0366. Min Range: -9.0366
Max Act: 8.0991. Min Act: -0.1699
Data Index: 2955278 (Open Web Text)
Max Activating Token Index: 884
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.0366. Min Range: -9.0366
Max Act: 8.0991. Min Act: -0.1700
Data Index: 7862134 (Open Web Text)
Max Activating Token Index: 84
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.0366. Min Range: -9.0366
Max Act: 8.0991. Min Act: -0.1700
Data Index: 4384859 (Open Web Text)
Max Activating Token Index: 1004
Click toggle to see full text
Truncated
Full Text #19