Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5965 in Layer 26
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.0341. Min Range: -5.0341
Max Act: 5.0341. Min Act: -0.1700
Data Index: 4203100 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0341. Min Range: -5.0341
Max Act: 4.7216. Min Act: -0.1700
Data Index: 1850717 (Open Web Text)
Max Activating Token Index: 893
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0341. Min Range: -5.0341
Max Act: 4.6279. Min Act: -0.1700
Data Index: 4827134 (Open Web Text)
Max Activating Token Index: 747
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0341. Min Range: -5.0341
Max Act: 4.5341. Min Act: -0.1700
Data Index: 6298112 (Open Web Text)
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0341. Min Range: -5.0341
Max Act: 4.5341. Min Act: -0.1700
Data Index: 8621510 (Open Web Text)
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0341. Min Range: -5.0341
Max Act: 4.5029. Min Act: -0.1700
Data Index: 670224 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0341. Min Range: -5.0341
Max Act: 4.4716. Min Act: -0.1700
Data Index: 307382 (Open Web Text)
Max Activating Token Index: 1016
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0341. Min Range: -5.0341
Max Act: 4.4716. Min Act: -0.1700
Data Index: 641726 (Open Web Text)
Max Activating Token Index: 874
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0341. Min Range: -5.0341
Max Act: 4.4716. Min Act: -0.1700
Data Index: 7966505 (Open Web Text)
Max Activating Token Index: 654
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0341. Min Range: -5.0341
Max Act: 4.4716. Min Act: -0.1700
Data Index: 3029348 (Open Web Text)
Max Activating Token Index: 751
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0341. Min Range: -5.0341
Max Act: 4.4716. Min Act: -0.1700
Data Index: 7767488 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0341. Min Range: -5.0341
Max Act: 4.4716. Min Act: -0.1700
Data Index: 1701232 (Open Web Text)
Max Activating Token Index: 253
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0341. Min Range: -5.0341
Max Act: 4.4716. Min Act: -0.1700
Data Index: 4622476 (Open Web Text)
Max Activating Token Index: 180
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0341. Min Range: -5.0341
Max Act: 4.4716. Min Act: -0.1700
Data Index: 8694277 (Open Web Text)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0341. Min Range: -5.0341
Max Act: 4.4716. Min Act: -0.1700
Data Index: 2568652 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0341. Min Range: -5.0341
Max Act: 4.4404. Min Act: -0.1700
Data Index: 8169509 (Open Web Text)
Max Activating Token Index: 926
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0341. Min Range: -5.0341
Max Act: 4.4404. Min Act: -0.1700
Data Index: 8398717 (Open Web Text)
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0341. Min Range: -5.0341
Max Act: 4.4404. Min Act: -0.1700
Data Index: 8481820 (Open Web Text)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0341. Min Range: -5.0341
Max Act: 4.4091. Min Act: -0.1700
Data Index: 7896618 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0341. Min Range: -5.0341
Max Act: 4.4091. Min Act: -0.1700
Data Index: 8177534 (Open Web Text)
Max Activating Token Index: 953
Click toggle to see full text
Truncated
Full Text #19