Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2848 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.0166. Min Range: -5.0166
Max Act: 5.0166. Min Act: -0.1700
Data Index: 5569539 (Open Web Text)
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0166. Min Range: -5.0166
Max Act: 4.8603. Min Act: -0.1700
Data Index: 3307456 (Open Web Text)
Max Activating Token Index: 141
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0166. Min Range: -5.0166
Max Act: 4.9228. Min Act: -0.1700
Data Index: 5761857 (Open Web Text)
Max Activating Token Index: 615
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0166. Min Range: -5.0166
Max Act: 4.8603. Min Act: -0.1700
Data Index: 6436048 (Open Web Text)
Max Activating Token Index: 906
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0166. Min Range: -5.0166
Max Act: 4.8916. Min Act: -0.1700
Data Index: 4773235 (Open Web Text)
Max Activating Token Index: 614
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0166. Min Range: -5.0166
Max Act: 4.8603. Min Act: -0.1700
Data Index: 6556453 (Open Web Text)
Max Activating Token Index: 499
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0166. Min Range: -5.0166
Max Act: 4.8291. Min Act: -0.1700
Data Index: 2863324 (Open Web Text)
Max Activating Token Index: 670
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0166. Min Range: -5.0166
Max Act: 4.7978. Min Act: -0.1700
Data Index: 7397770 (Open Web Text)
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0166. Min Range: -5.0166
Max Act: 4.7666. Min Act: -0.1700
Data Index: 1251461 (Open Web Text)
Max Activating Token Index: 689
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0166. Min Range: -5.0166
Max Act: 4.7353. Min Act: -0.1700
Data Index: 13203 (Open Web Text)
Max Activating Token Index: 482
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0166. Min Range: -5.0166
Max Act: 4.7353. Min Act: -0.1700
Data Index: 1342649 (Open Web Text)
Max Activating Token Index: 139
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0166. Min Range: -5.0166
Max Act: 4.7041. Min Act: -0.1700
Data Index: 6459069 (Open Web Text)
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0166. Min Range: -5.0166
Max Act: 4.7041. Min Act: -0.1700
Data Index: 1532257 (Open Web Text)
Max Activating Token Index: 594
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0166. Min Range: -5.0166
Max Act: 4.6728. Min Act: -0.1700
Data Index: 8542884 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0166. Min Range: -5.0166
Max Act: 4.6103. Min Act: -0.1700
Data Index: 4788871 (Open Web Text)
Max Activating Token Index: 869
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0166. Min Range: -5.0166
Max Act: 4.6103. Min Act: -0.1700
Data Index: 8288809 (Open Web Text)
Max Activating Token Index: 137
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0166. Min Range: -5.0166
Max Act: 4.6416. Min Act: -0.1700
Data Index: 755509 (Open Web Text)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0166. Min Range: -5.0166
Max Act: 4.6103. Min Act: -0.1700
Data Index: 8208475 (Open Web Text)
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0166. Min Range: -5.0166
Max Act: 4.5791. Min Act: -0.1700
Data Index: 3708572 (Open Web Text)
Max Activating Token Index: 274
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0166. Min Range: -5.0166
Max Act: 4.6103. Min Act: -0.1700
Data Index: 7342930 (Open Web Text)
Max Activating Token Index: 513
Click toggle to see full text
Truncated
Full Text #19