Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2108 in Layer 13
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 2.9729. Min Range: -2.9729
Max Act: 2.9729. Min Act: -0.1700
Data Index: 4671478 (Open Web Text)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.9729. Min Range: -2.9729
Max Act: 2.9571. Min Act: -0.1700
Data Index: 8775724 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.9729. Min Range: -2.9729
Max Act: 2.9729. Min Act: -0.1700
Data Index: 5063963 (Open Web Text)
Max Activating Token Index: 649
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.9729. Min Range: -2.9729
Max Act: 2.9571. Min Act: -0.1700
Data Index: 1598155 (Open Web Text)
Max Activating Token Index: 585
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.9729. Min Range: -2.9729
Max Act: 2.9254. Min Act: -0.1700
Data Index: 5959713 (Open Web Text)
Max Activating Token Index: 853
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.9729. Min Range: -2.9729
Max Act: 2.8779. Min Act: -0.1700
Data Index: 816392 (Open Web Text)
Max Activating Token Index: 847
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.9729. Min Range: -2.9729
Max Act: 2.8937. Min Act: -0.1700
Data Index: 5353258 (Open Web Text)
Max Activating Token Index: 619
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.9729. Min Range: -2.9729
Max Act: 2.9096. Min Act: -0.1700
Data Index: 7031651 (Open Web Text)
Max Activating Token Index: 698
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.9729. Min Range: -2.9729
Max Act: 2.8937. Min Act: -0.1700
Data Index: 2306626 (Open Web Text)
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.9729. Min Range: -2.9729
Max Act: 2.8779. Min Act: -0.1700
Data Index: 2910230 (Open Web Text)
Max Activating Token Index: 116
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.9729. Min Range: -2.9729
Max Act: 2.8937. Min Act: -0.1700
Data Index: 5943934 (Open Web Text)
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.9729. Min Range: -2.9729
Max Act: 2.8620. Min Act: -0.1700
Data Index: 3022035 (Open Web Text)
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.9729. Min Range: -2.9729
Max Act: 2.8620. Min Act: -0.1700
Data Index: 4039412 (Open Web Text)
Max Activating Token Index: 779
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.9729. Min Range: -2.9729
Max Act: 2.8779. Min Act: -0.1700
Data Index: 1743888 (Open Web Text)
Max Activating Token Index: 692
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.9729. Min Range: -2.9729
Max Act: 2.8461. Min Act: -0.1700
Data Index: 4527066 (Open Web Text)
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.9729. Min Range: -2.9729
Max Act: 2.8302. Min Act: -0.1700
Data Index: 5748884 (Open Web Text)
Max Activating Token Index: 409
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.9729. Min Range: -2.9729
Max Act: 2.8620. Min Act: -0.1700
Data Index: 6662436 (Open Web Text)
Max Activating Token Index: 539
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.9729. Min Range: -2.9729
Max Act: 2.8461. Min Act: -0.1700
Data Index: 4682875 (Open Web Text)
Max Activating Token Index: 246
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.9729. Min Range: -2.9729
Max Act: 2.8302. Min Act: -0.1700
Data Index: 3095595 (Open Web Text)
Max Activating Token Index: 55
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.9729. Min Range: -2.9729
Max Act: 2.8779. Min Act: -0.1700
Data Index: 7191402 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #19