Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3457 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 9.0448. Min Range: -9.0448
Max Act: 9.0448. Min Act: -0.1700
Data Index: 8738571 (Open Web Text)
Max Activating Token Index: 568
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.0448. Min Range: -9.0448
Max Act: 8.8573. Min Act: -0.1700
Data Index: 2845190 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.0448. Min Range: -9.0448
Max Act: 8.6073. Min Act: -0.1700
Data Index: 8616617 (Open Web Text)
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.0448. Min Range: -9.0448
Max Act: 8.6698. Min Act: -0.1700
Data Index: 7552628 (Open Web Text)
Max Activating Token Index: 63
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.0448. Min Range: -9.0448
Max Act: 8.6073. Min Act: -0.1700
Data Index: 3645985 (Open Web Text)
Max Activating Token Index: 891
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.0448. Min Range: -9.0448
Max Act: 8.5448. Min Act: -0.1700
Data Index: 1630096 (Open Web Text)
Max Activating Token Index: 776
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.0448. Min Range: -9.0448
Max Act: 8.5448. Min Act: -0.1700
Data Index: 4007226 (Open Web Text)
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.0448. Min Range: -9.0448
Max Act: 8.4823. Min Act: -0.1700
Data Index: 5231909 (Open Web Text)
Max Activating Token Index: 933
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.0448. Min Range: -9.0448
Max Act: 8.4823. Min Act: -0.1700
Data Index: 538218 (Open Web Text)
Max Activating Token Index: 706
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.0448. Min Range: -9.0448
Max Act: 8.4198. Min Act: -0.1700
Data Index: 7872724 (Open Web Text)
Max Activating Token Index: 130
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.0448. Min Range: -9.0448
Max Act: 8.4823. Min Act: -0.1700
Data Index: 2840553 (Open Web Text)
Max Activating Token Index: 422
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.0448. Min Range: -9.0448
Max Act: 8.4823. Min Act: -0.1700
Data Index: 1644965 (Open Web Text)
Max Activating Token Index: 330
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.0448. Min Range: -9.0448
Max Act: 8.4198. Min Act: -0.1700
Data Index: 6401072 (Open Web Text)
Max Activating Token Index: 308
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.0448. Min Range: -9.0448
Max Act: 8.4198. Min Act: -0.1700
Data Index: 5990048 (Open Web Text)
Max Activating Token Index: 846
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.0448. Min Range: -9.0448
Max Act: 8.3573. Min Act: -0.1700
Data Index: 5567523 (Open Web Text)
Max Activating Token Index: 380
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.0448. Min Range: -9.0448
Max Act: 8.3573. Min Act: -0.1700
Data Index: 595032 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.0448. Min Range: -9.0448
Max Act: 8.3573. Min Act: -0.1700
Data Index: 366687 (Open Web Text)
Max Activating Token Index: 788
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.0448. Min Range: -9.0448
Max Act: 8.3573. Min Act: -0.1700
Data Index: 5082147 (Open Web Text)
Max Activating Token Index: 425
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.0448. Min Range: -9.0448
Max Act: 8.4198. Min Act: -0.1700
Data Index: 3087224 (Open Web Text)
Max Activating Token Index: 604
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.0448. Min Range: -9.0448
Max Act: 8.3573. Min Act: -0.1700
Data Index: 4003458 (Open Web Text)
Max Activating Token Index: 592
Click toggle to see full text
Truncated
Full Text #19