Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 1227 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 7.2328. Min Range: -7.2328
Max Act: 7.2328. Min Act: -0.1700
Data Index: 4852364 (Open Web Text)
Max Activating Token Index: 816
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.2328. Min Range: -7.2328
Max Act: 7.1391. Min Act: -0.1700
Data Index: 3959847 (Open Web Text)
Max Activating Token Index: 400
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.2328. Min Range: -7.2328
Max Act: 7.0766. Min Act: -0.1700
Data Index: 7040067 (Open Web Text)
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.2328. Min Range: -7.2328
Max Act: 7.0141. Min Act: -0.1700
Data Index: 3610325 (Open Web Text)
Max Activating Token Index: 857
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.2328. Min Range: -7.2328
Max Act: 6.9516. Min Act: -0.1700
Data Index: 553116 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.2328. Min Range: -7.2328
Max Act: 6.8578. Min Act: -0.1700
Data Index: 3142721 (Open Web Text)
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.2328. Min Range: -7.2328
Max Act: 6.8266. Min Act: -0.1700
Data Index: 5225372 (Open Web Text)
Max Activating Token Index: 917
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.2328. Min Range: -7.2328
Max Act: 6.7953. Min Act: -0.1700
Data Index: 3853719 (Open Web Text)
Max Activating Token Index: 611
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.2328. Min Range: -7.2328
Max Act: 6.7328. Min Act: -0.1700
Data Index: 146454 (Open Web Text)
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.2328. Min Range: -7.2328
Max Act: 6.7328. Min Act: -0.1700
Data Index: 3648822 (Open Web Text)
Max Activating Token Index: 960
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.2328. Min Range: -7.2328
Max Act: 6.7641. Min Act: -0.1700
Data Index: 739202 (Open Web Text)
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.2328. Min Range: -7.2328
Max Act: 6.6703. Min Act: -0.1700
Data Index: 1767707 (Open Web Text)
Max Activating Token Index: 268
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.2328. Min Range: -7.2328
Max Act: 6.7016. Min Act: -0.1700
Data Index: 1195658 (Open Web Text)
Max Activating Token Index: 123
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.2328. Min Range: -7.2328
Max Act: 6.6703. Min Act: -0.1700
Data Index: 1676482 (Open Web Text)
Max Activating Token Index: 751
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.2328. Min Range: -7.2328
Max Act: 6.7016. Min Act: -0.1700
Data Index: 7552337 (Open Web Text)
Max Activating Token Index: 852
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.2328. Min Range: -7.2328
Max Act: 6.7016. Min Act: -0.1700
Data Index: 5317279 (Open Web Text)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.2328. Min Range: -7.2328
Max Act: 6.7328. Min Act: -0.1700
Data Index: 910426 (Open Web Text)
Max Activating Token Index: 899
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.2328. Min Range: -7.2328
Max Act: 6.6391. Min Act: -0.1700
Data Index: 128999 (Open Web Text)
Max Activating Token Index: 702
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.2328. Min Range: -7.2328
Max Act: 6.7016. Min Act: -0.1700
Data Index: 8659626 (Open Web Text)
Max Activating Token Index: 711
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.2328. Min Range: -7.2328
Max Act: 6.6078. Min Act: -0.1700
Data Index: 3894128 (Open Web Text)
Max Activating Token Index: 515
Click toggle to see full text
Truncated
Full Text #19