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

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

Neuron 4068 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.5200. Min Range: -4.5200

Max Act: 4.5200. Min Act: -0.0000

Data Index: 368867 (C4 (Web Text))

Max Activating Token Index: 287

Text #1

Max Range: 4.5200. Min Range: -4.5200

Max Act: 4.1107. Min Act: -0.0000

Data Index: 1082478 (C4 (Web Text))

Max Activating Token Index: 437

Text #2

Max Range: 4.5200. Min Range: -4.5200

Max Act: 3.7467. Min Act: -0.0000

Data Index: 481335 (C4 (Web Text))

Max Activating Token Index: 735

Text #3

Max Range: 4.5200. Min Range: -4.5200

Max Act: 3.6893. Min Act: -0.0000

Data Index: 519721 (C4 (Web Text))

Max Activating Token Index: 939

Text #4

Max Range: 4.5200. Min Range: -4.5200

Max Act: 3.4866. Min Act: -0.0000

Data Index: 693524 (C4 (Web Text))

Max Activating Token Index: 92

Text #5

Max Range: 4.5200. Min Range: -4.5200

Max Act: 3.4883. Min Act: -0.0000

Data Index: 177684 (C4 (Web Text))

Max Activating Token Index: 267

Text #6

Max Range: 4.5200. Min Range: -4.5200

Max Act: 3.3003. Min Act: -0.0000

Data Index: 217817 (C4 (Web Text))

Max Activating Token Index: 700

Text #7

Max Range: 4.5200. Min Range: -4.5200

Max Act: 3.2874. Min Act: -0.0000

Data Index: 728791 (C4 (Web Text))

Max Activating Token Index: 126

Text #8

Max Range: 4.5200. Min Range: -4.5200

Max Act: 2.9182. Min Act: -0.0000

Data Index: 1243286 (C4 (Web Text))

Max Activating Token Index: 930

Text #9

Max Range: 4.5200. Min Range: -4.5200

Max Act: 2.6985. Min Act: -0.0000

Data Index: 621318 (C4 (Web Text))

Max Activating Token Index: 889

Text #10

Max Range: 4.5200. Min Range: -4.5200

Max Act: 2.7476. Min Act: -0.0000

Data Index: 543729 (C4 (Web Text))

Max Activating Token Index: 929

Text #11

Max Range: 4.5200. Min Range: -4.5200

Max Act: 3.0369. Min Act: -0.0000

Data Index: 777637 (C4 (Web Text))

Max Activating Token Index: 768

Text #12

Max Range: 4.5200. Min Range: -4.5200

Max Act: 2.5630. Min Act: -0.0000

Data Index: 383040 (C4 (Web Text))

Max Activating Token Index: 105

Text #13

Max Range: 4.5200. Min Range: -4.5200

Max Act: 2.5230. Min Act: -0.0000

Data Index: 22893 (C4 (Web Text))

Max Activating Token Index: 74

Text #14

Max Range: 4.5200. Min Range: -4.5200

Max Act: 2.6465. Min Act: -0.0000

Data Index: 1229828 (C4 (Web Text))

Max Activating Token Index: 87

Text #15

Max Range: 4.5200. Min Range: -4.5200

Max Act: 2.7689. Min Act: -0.0000

Data Index: 526571 (C4 (Web Text))

Max Activating Token Index: 22

Text #16

Max Range: 4.5200. Min Range: -4.5200

Max Act: 2.5052. Min Act: -0.0000

Data Index: 1271413 (C4 (Web Text))

Max Activating Token Index: 62

Text #17

Max Range: 4.5200. Min Range: -4.5200

Max Act: 2.4363. Min Act: -0.0000

Data Index: 140219 (C4 (Web Text))

Max Activating Token Index: 765

Text #18

Max Range: 4.5200. Min Range: -4.5200

Max Act: 2.5622. Min Act: -0.0000

Data Index: 388772 (C4 (Web Text))

Max Activating Token Index: 121

Text #19

Max Range: 4.5200. Min Range: -4.5200

Max Act: 2.5566. Min Act: -0.0000

Data Index: 721216 (C4 (Web Text))

Max Activating Token Index: 73