Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 5544 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 1.7916. Min Range: -1.7916

Max Act: 1.7916. Min Act: -0.0000

Data Index: 973164 (C4 (Web Text))

Max Activating Token Index: 740

Text #1

Max Range: 1.7916. Min Range: -1.7916

Max Act: 1.6427. Min Act: -0.0000

Data Index: 326824 (C4 (Web Text))

Max Activating Token Index: 918

Text #2

Max Range: 1.7916. Min Range: -1.7916

Max Act: 1.6210. Min Act: -0.0000

Data Index: 1239228 (C4 (Web Text))

Max Activating Token Index: 986

Text #3

Max Range: 1.7916. Min Range: -1.7916

Max Act: 1.5596. Min Act: -0.0000

Data Index: 1316429 (C4 (Web Text))

Max Activating Token Index: 674

Text #4

Max Range: 1.7916. Min Range: -1.7916

Max Act: 1.5336. Min Act: -0.0000

Data Index: 668335 (C4 (Web Text))

Max Activating Token Index: 816

Text #5

Max Range: 1.7916. Min Range: -1.7916

Max Act: 1.3478. Min Act: -0.0000

Data Index: 1301753 (C4 (Web Text))

Max Activating Token Index: 837

Text #6

Max Range: 1.7916. Min Range: -1.7916

Max Act: 1.5071. Min Act: -0.0000

Data Index: 481699 (C4 (Web Text))

Max Activating Token Index: 916

Text #7

Max Range: 1.7916. Min Range: -1.7916

Max Act: 1.4947. Min Act: -0.0000

Data Index: 169077 (C4 (Web Text))

Max Activating Token Index: 904

Text #8

Max Range: 1.7916. Min Range: -1.7916

Max Act: 1.4846. Min Act: -0.0000

Data Index: 378828 (C4 (Web Text))

Max Activating Token Index: 1003

Text #9

Max Range: 1.7916. Min Range: -1.7916

Max Act: 1.5837. Min Act: -0.0000

Data Index: 731712 (C4 (Web Text))

Max Activating Token Index: 949

Text #10

Max Range: 1.7916. Min Range: -1.7916

Max Act: 1.4637. Min Act: -0.0000

Data Index: 1212850 (C4 (Web Text))

Max Activating Token Index: 589

Text #11

Max Range: 1.7916. Min Range: -1.7916

Max Act: 1.3757. Min Act: -0.0000

Data Index: 1106315 (C4 (Web Text))

Max Activating Token Index: 795

Text #12

Max Range: 1.7916. Min Range: -1.7916

Max Act: 1.4464. Min Act: -0.0000

Data Index: 487272 (C4 (Web Text))

Max Activating Token Index: 535

Text #13

Max Range: 1.7916. Min Range: -1.7916

Max Act: 1.3498. Min Act: -0.0000

Data Index: 464677 (C4 (Web Text))

Max Activating Token Index: 957

Text #14

Max Range: 1.7916. Min Range: -1.7916

Max Act: 1.2629. Min Act: -0.0000

Data Index: 1165713 (C4 (Web Text))

Max Activating Token Index: 859

Text #15

Max Range: 1.7916. Min Range: -1.7916

Max Act: 1.2993. Min Act: -0.0000

Data Index: 195426 (C4 (Web Text))

Max Activating Token Index: 888

Text #16

Max Range: 1.7916. Min Range: -1.7916

Max Act: 1.2826. Min Act: -0.0000

Data Index: 860240 (C4 (Web Text))

Max Activating Token Index: 998

Text #17

Max Range: 1.7916. Min Range: -1.7916

Max Act: 1.3901. Min Act: -0.0000

Data Index: 728454 (C4 (Web Text))

Max Activating Token Index: 580

Text #18

Max Range: 1.7916. Min Range: -1.7916

Max Act: 1.3586. Min Act: -0.0000

Data Index: 1189189 (C4 (Web Text))

Max Activating Token Index: 648

Text #19

Max Range: 1.7916. Min Range: -1.7916

Max Act: 1.2678. Min Act: -0.0000

Data Index: 795210 (C4 (Web Text))

Max Activating Token Index: 605