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

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

Neuron 1076 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: 2.6965. Min Range: -2.6965

Max Act: 2.5633. Min Act: -0.0000

Data Index: 1414100 (Python Code)

Max Activating Token Index: 557

Text #1

Max Range: 2.6965. Min Range: -2.6965

Max Act: 2.5227. Min Act: -0.0000

Data Index: 1279153 (C4 (Web Text))

Max Activating Token Index: 69

Text #2

Max Range: 2.6965. Min Range: -2.6965

Max Act: 2.5732. Min Act: -0.0000

Data Index: 1398035 (Python Code)

Max Activating Token Index: 817

Text #3

Max Range: 2.6965. Min Range: -2.6965

Max Act: 2.6965. Min Act: -0.0000

Data Index: 1438566 (Python Code)

Max Activating Token Index: 101

Text #4

Max Range: 2.6965. Min Range: -2.6965

Max Act: 2.5280. Min Act: -0.0000

Data Index: 900888 (C4 (Web Text))

Max Activating Token Index: 623

Text #5

Max Range: 2.6965. Min Range: -2.6965

Max Act: 2.5097. Min Act: -0.0000

Data Index: 1535059 (Python Code)

Max Activating Token Index: 666

Text #6

Max Range: 2.6965. Min Range: -2.6965

Max Act: 2.6182. Min Act: -0.0000

Data Index: 434498 (C4 (Web Text))

Max Activating Token Index: 678

Text #7

Max Range: 2.6965. Min Range: -2.6965

Max Act: 2.4434. Min Act: -0.0000

Data Index: 1578647 (Python Code)

Max Activating Token Index: 625

Text #8

Max Range: 2.6965. Min Range: -2.6965

Max Act: 2.4538. Min Act: -0.0000

Data Index: 918360 (C4 (Web Text))

Max Activating Token Index: 86

Text #9

Max Range: 2.6965. Min Range: -2.6965

Max Act: 2.2141. Min Act: -0.0000

Data Index: 1440144 (Python Code)

Max Activating Token Index: 378

Text #10

Max Range: 2.6965. Min Range: -2.6965

Max Act: 2.3122. Min Act: -0.0000

Data Index: 1577391 (Python Code)

Max Activating Token Index: 157

Text #11

Max Range: 2.6965. Min Range: -2.6965

Max Act: 2.4080. Min Act: -0.0000

Data Index: 1501707 (Python Code)

Max Activating Token Index: 225

Text #12

Max Range: 2.6965. Min Range: -2.6965

Max Act: 2.3694. Min Act: -0.0000

Data Index: 1036971 (C4 (Web Text))

Max Activating Token Index: 764

Text #13

Max Range: 2.6965. Min Range: -2.6965

Max Act: 2.3600. Min Act: -0.0000

Data Index: 738646 (C4 (Web Text))

Max Activating Token Index: 908

Text #14

Max Range: 2.6965. Min Range: -2.6965

Max Act: 2.3345. Min Act: -0.0000

Data Index: 686753 (C4 (Web Text))

Max Activating Token Index: 627

Text #15

Max Range: 2.6965. Min Range: -2.6965

Max Act: 2.2380. Min Act: -0.0000

Data Index: 493879 (C4 (Web Text))

Max Activating Token Index: 284

Text #16

Max Range: 2.6965. Min Range: -2.6965

Max Act: 2.3375. Min Act: -0.0000

Data Index: 42981 (C4 (Web Text))

Max Activating Token Index: 229

Text #17

Max Range: 2.6965. Min Range: -2.6965

Max Act: 2.4205. Min Act: -0.0000

Data Index: 485724 (C4 (Web Text))

Max Activating Token Index: 851

Text #18

Max Range: 2.6965. Min Range: -2.6965

Max Act: 2.4568. Min Act: -0.0000

Data Index: 1475219 (Python Code)

Max Activating Token Index: 754

Text #19

Max Range: 2.6965. Min Range: -2.6965

Max Act: 2.2050. Min Act: -0.0000

Data Index: 1567176 (Python Code)

Max Activating Token Index: 146