Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 1636 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 4.3978. Min Range: -4.3978

Max Act: 4.3978. Min Act: -0.0002

Data Index: 547511 (C4 (Web Text))

Max Activating Token Index: 871

Text #1

Max Range: 4.3978. Min Range: -4.3978

Max Act: 3.9875. Min Act: -0.0002

Data Index: 515116 (C4 (Web Text))

Max Activating Token Index: 703

Text #2

Max Range: 4.3978. Min Range: -4.3978

Max Act: 3.7046. Min Act: -0.0002

Data Index: 74790 (C4 (Web Text))

Max Activating Token Index: 318

Text #3

Max Range: 4.3978. Min Range: -4.3978

Max Act: 3.9241. Min Act: -0.0002

Data Index: 630513 (C4 (Web Text))

Max Activating Token Index: 678

Text #4

Max Range: 4.3978. Min Range: -4.3978

Max Act: 3.8947. Min Act: -0.0002

Data Index: 51574 (C4 (Web Text))

Max Activating Token Index: 929

Text #5

Max Range: 4.3978. Min Range: -4.3978

Max Act: 3.5697. Min Act: -0.0002

Data Index: 1341985 (C4 (Web Text))

Max Activating Token Index: 377

Text #6

Max Range: 4.3978. Min Range: -4.3978

Max Act: 3.2024. Min Act: -0.0002

Data Index: 1182446 (C4 (Web Text))

Max Activating Token Index: 673

Text #7

Max Range: 4.3978. Min Range: -4.3978

Max Act: 3.2756. Min Act: -0.0002

Data Index: 730729 (C4 (Web Text))

Max Activating Token Index: 61

Text #8

Max Range: 4.3978. Min Range: -4.3978

Max Act: 3.5413. Min Act: -0.0002

Data Index: 1357319 (C4 (Web Text))

Max Activating Token Index: 977

Text #9

Max Range: 4.3978. Min Range: -4.3978

Max Act: 3.3935. Min Act: -0.0002

Data Index: 174665 (C4 (Web Text))

Max Activating Token Index: 1011

Text #10

Max Range: 4.3978. Min Range: -4.3978

Max Act: 3.6620. Min Act: -0.0002

Data Index: 1031009 (C4 (Web Text))

Max Activating Token Index: 946

Text #11

Max Range: 4.3978. Min Range: -4.3978

Max Act: 3.1985. Min Act: -0.0002

Data Index: 1077683 (C4 (Web Text))

Max Activating Token Index: 776

Text #12

Max Range: 4.3978. Min Range: -4.3978

Max Act: 3.5933. Min Act: -0.0002

Data Index: 140508 (C4 (Web Text))

Max Activating Token Index: 869

Text #13

Max Range: 4.3978. Min Range: -4.3978

Max Act: 3.1297. Min Act: -0.0002

Data Index: 843545 (C4 (Web Text))

Max Activating Token Index: 722

Text #14

Max Range: 4.3978. Min Range: -4.3978

Max Act: 3.5629. Min Act: -0.0002

Data Index: 699821 (C4 (Web Text))

Max Activating Token Index: 606

Text #15

Max Range: 4.3978. Min Range: -4.3978

Max Act: 2.9976. Min Act: -0.0002

Data Index: 179669 (C4 (Web Text))

Max Activating Token Index: 411

Text #16

Max Range: 4.3978. Min Range: -4.3978

Max Act: 3.0169. Min Act: -0.0002

Data Index: 804565 (C4 (Web Text))

Max Activating Token Index: 183

Text #17

Max Range: 4.3978. Min Range: -4.3978

Max Act: 3.2161. Min Act: -0.0002

Data Index: 49458 (C4 (Web Text))

Max Activating Token Index: 764

Text #18

Max Range: 4.3978. Min Range: -4.3978

Max Act: 3.0960. Min Act: -0.0002

Data Index: 1227914 (C4 (Web Text))

Max Activating Token Index: 621

Text #19

Max Range: 4.3978. Min Range: -4.3978

Max Act: 3.2176. Min Act: -0.0002

Data Index: 59365 (C4 (Web Text))

Max Activating Token Index: 694