Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3371 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.1717. Min Range: -5.1717
Max Act: 5.1717. Min Act: -0.1700
Data Index: 4940539 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.1717. Min Range: -5.1717
Max Act: 5.1717. Min Act: -0.1700
Data Index: 5011256 (Open Web Text)
Max Activating Token Index: 891
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.1717. Min Range: -5.1717
Max Act: 5.1404. Min Act: -0.1700
Data Index: 536281 (Open Web Text)
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.1717. Min Range: -5.1717
Max Act: 5.1404. Min Act: -0.1700
Data Index: 6672001 (Open Web Text)
Max Activating Token Index: 572
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.1717. Min Range: -5.1717
Max Act: 5.1404. Min Act: -0.1700
Data Index: 3919358 (Open Web Text)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.1717. Min Range: -5.1717
Max Act: 5.1404. Min Act: -0.1700
Data Index: 567850 (Open Web Text)
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.1717. Min Range: -5.1717
Max Act: 5.0779. Min Act: -0.1700
Data Index: 4612819 (Open Web Text)
Max Activating Token Index: 899
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.1717. Min Range: -5.1717
Max Act: 5.1404. Min Act: -0.1700
Data Index: 8250734 (Open Web Text)
Max Activating Token Index: 236
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.1717. Min Range: -5.1717
Max Act: 5.1092. Min Act: -0.1700
Data Index: 14698 (Open Web Text)
Max Activating Token Index: 982
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.1717. Min Range: -5.1717
Max Act: 5.1092. Min Act: -0.1700
Data Index: 2637361 (Open Web Text)
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.1717. Min Range: -5.1717
Max Act: 5.1092. Min Act: -0.1700
Data Index: 7939748 (Open Web Text)
Max Activating Token Index: 271
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.1717. Min Range: -5.1717
Max Act: 5.0467. Min Act: -0.1700
Data Index: 4089285 (Open Web Text)
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.1717. Min Range: -5.1717
Max Act: 5.0779. Min Act: -0.1700
Data Index: 7508834 (Open Web Text)
Max Activating Token Index: 543
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.1717. Min Range: -5.1717
Max Act: 5.0467. Min Act: -0.1700
Data Index: 1930161 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.1717. Min Range: -5.1717
Max Act: 5.0467. Min Act: -0.1700
Data Index: 2786497 (Open Web Text)
Max Activating Token Index: 999
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.1717. Min Range: -5.1717
Max Act: 5.0467. Min Act: -0.1700
Data Index: 5168373 (Open Web Text)
Max Activating Token Index: 244
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.1717. Min Range: -5.1717
Max Act: 5.0467. Min Act: -0.1700
Data Index: 3318979 (Open Web Text)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.1717. Min Range: -5.1717
Max Act: 5.0154. Min Act: -0.1700
Data Index: 6626108 (Open Web Text)
Max Activating Token Index: 39
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.1717. Min Range: -5.1717
Max Act: 5.0154. Min Act: -0.1700
Data Index: 7617959 (Open Web Text)
Max Activating Token Index: 765
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.1717. Min Range: -5.1717
Max Act: 5.0467. Min Act: -0.1700
Data Index: 7160847 (Open Web Text)
Max Activating Token Index: 425
Click toggle to see full text
Truncated
Full Text #19