Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1502 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.4533. Min Range: -5.4533
Max Act: 5.4221. Min Act: -0.1700
Data Index: 87270 (Open Web Text)
Max Activating Token Index: 783
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.4533. Min Range: -5.4533
Max Act: 5.4533. Min Act: -0.1700
Data Index: 7736071 (Open Web Text)
Max Activating Token Index: 165
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.4533. Min Range: -5.4533
Max Act: 5.3908. Min Act: -0.1700
Data Index: 4525914 (Open Web Text)
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.4533. Min Range: -5.4533
Max Act: 5.3283. Min Act: -0.1700
Data Index: 2848462 (Open Web Text)
Max Activating Token Index: 925
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.4533. Min Range: -5.4533
Max Act: 5.3283. Min Act: -0.1700
Data Index: 5751416 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.4533. Min Range: -5.4533
Max Act: 5.2346. Min Act: -0.1700
Data Index: 5712533 (Open Web Text)
Max Activating Token Index: 284
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.4533. Min Range: -5.4533
Max Act: 5.2346. Min Act: -0.1700
Data Index: 1377828 (Open Web Text)
Max Activating Token Index: 686
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.4533. Min Range: -5.4533
Max Act: 5.2033. Min Act: -0.1700
Data Index: 2694785 (Open Web Text)
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.4533. Min Range: -5.4533
Max Act: 5.2033. Min Act: -0.1700
Data Index: 50993 (Open Web Text)
Max Activating Token Index: 649
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.4533. Min Range: -5.4533
Max Act: 5.1721. Min Act: -0.1700
Data Index: 5433061 (Open Web Text)
Max Activating Token Index: 834
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.4533. Min Range: -5.4533
Max Act: 5.1096. Min Act: -0.1700
Data Index: 8475321 (Open Web Text)
Max Activating Token Index: 265
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.4533. Min Range: -5.4533
Max Act: 5.1408. Min Act: -0.1700
Data Index: 6233575 (Open Web Text)
Max Activating Token Index: 837
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.4533. Min Range: -5.4533
Max Act: 5.1721. Min Act: -0.1700
Data Index: 2181537 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.4533. Min Range: -5.4533
Max Act: 5.1408. Min Act: -0.1700
Data Index: 6575533 (Open Web Text)
Max Activating Token Index: 811
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.4533. Min Range: -5.4533
Max Act: 5.1096. Min Act: -0.1700
Data Index: 8586346 (Open Web Text)
Max Activating Token Index: 858
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.4533. Min Range: -5.4533
Max Act: 5.0783. Min Act: -0.1700
Data Index: 8784800 (Open Web Text)
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.4533. Min Range: -5.4533
Max Act: 5.0158. Min Act: -0.1700
Data Index: 7355090 (Open Web Text)
Max Activating Token Index: 453
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.4533. Min Range: -5.4533
Max Act: 5.0783. Min Act: -0.1700
Data Index: 5827940 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.4533. Min Range: -5.4533
Max Act: 5.0783. Min Act: -0.1700
Data Index: 5831360 (Open Web Text)
Max Activating Token Index: 564
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.4533. Min Range: -5.4533
Max Act: 5.0783. Min Act: -0.1700
Data Index: 3052401 (Open Web Text)
Max Activating Token Index: 396
Click toggle to see full text
Truncated
Full Text #19