Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3417 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.1122. Min Range: -5.1122
Max Act: 5.1122. Min Act: -0.1700
Data Index: 1230113 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.1122. Min Range: -5.1122
Max Act: 4.9872. Min Act: -0.1700
Data Index: 7873984 (Open Web Text)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.1122. Min Range: -5.1122
Max Act: 4.8622. Min Act: -0.1700
Data Index: 7916171 (Open Web Text)
Max Activating Token Index: 335
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.1122. Min Range: -5.1122
Max Act: 4.8309. Min Act: -0.1700
Data Index: 4259148 (Open Web Text)
Max Activating Token Index: 330
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.1122. Min Range: -5.1122
Max Act: 4.8309. Min Act: -0.1700
Data Index: 890814 (Open Web Text)
Max Activating Token Index: 688
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.1122. Min Range: -5.1122
Max Act: 4.8309. Min Act: -0.1700
Data Index: 4681997 (Open Web Text)
Max Activating Token Index: 895
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.1122. Min Range: -5.1122
Max Act: 4.7997. Min Act: -0.1700
Data Index: 7771004 (Open Web Text)
Max Activating Token Index: 869
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.1122. Min Range: -5.1122
Max Act: 4.7997. Min Act: -0.1700
Data Index: 409184 (Open Web Text)
Max Activating Token Index: 425
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.1122. Min Range: -5.1122
Max Act: 4.8309. Min Act: -0.1700
Data Index: 5027874 (Open Web Text)
Max Activating Token Index: 978
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.1122. Min Range: -5.1122
Max Act: 4.7684. Min Act: -0.1700
Data Index: 2230792 (Open Web Text)
Max Activating Token Index: 838
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.1122. Min Range: -5.1122
Max Act: 4.7997. Min Act: -0.1700
Data Index: 2636646 (Open Web Text)
Max Activating Token Index: 397
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.1122. Min Range: -5.1122
Max Act: 4.7684. Min Act: -0.1700
Data Index: 6868445 (Open Web Text)
Max Activating Token Index: 195
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.1122. Min Range: -5.1122
Max Act: 4.7684. Min Act: -0.1700
Data Index: 5117228 (Open Web Text)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.1122. Min Range: -5.1122
Max Act: 4.7684. Min Act: -0.1700
Data Index: 3648111 (Open Web Text)
Max Activating Token Index: 311
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.1122. Min Range: -5.1122
Max Act: 4.7372. Min Act: -0.1700
Data Index: 8057915 (Open Web Text)
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.1122. Min Range: -5.1122
Max Act: 4.7372. Min Act: -0.1700
Data Index: 7607901 (Open Web Text)
Max Activating Token Index: 530
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.1122. Min Range: -5.1122
Max Act: 4.7372. Min Act: -0.1700
Data Index: 6923016 (Open Web Text)
Max Activating Token Index: 626
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.1122. Min Range: -5.1122
Max Act: 4.7059. Min Act: -0.1700
Data Index: 2152795 (Open Web Text)
Max Activating Token Index: 1006
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.1122. Min Range: -5.1122
Max Act: 4.7059. Min Act: -0.1700
Data Index: 3098555 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.1122. Min Range: -5.1122
Max Act: 4.6747. Min Act: -0.1700
Data Index: 6358090 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #19