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

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

Neuron 3984 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: 0.4397. Min Range: -0.4397

Max Act: 0.4280. Min Act: -0.0002

Data Index: 1503327 (Python Code)

Max Activating Token Index: 931

Text #1

Max Range: 0.4397. Min Range: -0.4397

Max Act: 0.4397. Min Act: -0.0002

Data Index: 1224076 (C4 (Web Text))

Max Activating Token Index: 4

Text #2

Max Range: 0.4397. Min Range: -0.4397

Max Act: 0.4259. Min Act: -0.0002

Data Index: 377884 (C4 (Web Text))

Max Activating Token Index: 1018

Text #3

Max Range: 0.4397. Min Range: -0.4397

Max Act: 0.3984. Min Act: -0.0002

Data Index: 918071 (C4 (Web Text))

Max Activating Token Index: 3

Text #4

Max Range: 0.4397. Min Range: -0.4397

Max Act: 0.3746. Min Act: -0.0002

Data Index: 959166 (C4 (Web Text))

Max Activating Token Index: 987

Text #5

Max Range: 0.4397. Min Range: -0.4397

Max Act: 0.4135. Min Act: -0.0002

Data Index: 609354 (C4 (Web Text))

Max Activating Token Index: 30

Text #6

Max Range: 0.4397. Min Range: -0.4397

Max Act: 0.4080. Min Act: -0.0002

Data Index: 1030001 (C4 (Web Text))

Max Activating Token Index: 921

Text #7

Max Range: 0.4397. Min Range: -0.4397

Max Act: 0.3844. Min Act: -0.0002

Data Index: 389583 (C4 (Web Text))

Max Activating Token Index: 9

Text #8

Max Range: 0.4397. Min Range: -0.4397

Max Act: 0.3838. Min Act: -0.0002

Data Index: 976898 (C4 (Web Text))

Max Activating Token Index: 58

Text #9

Max Range: 0.4397. Min Range: -0.4397

Max Act: 0.3497. Min Act: -0.0002

Data Index: 689539 (C4 (Web Text))

Max Activating Token Index: 535

Text #10

Max Range: 0.4397. Min Range: -0.4397

Max Act: 0.3677. Min Act: -0.0002

Data Index: 804029 (C4 (Web Text))

Max Activating Token Index: 20

Text #11

Max Range: 0.4397. Min Range: -0.4397

Max Act: 0.3690. Min Act: -0.0002

Data Index: 1244797 (C4 (Web Text))

Max Activating Token Index: 4

Text #12

Max Range: 0.4397. Min Range: -0.4397

Max Act: 0.3866. Min Act: -0.0002

Data Index: 330220 (C4 (Web Text))

Max Activating Token Index: 129

Text #13

Max Range: 0.4397. Min Range: -0.4397

Max Act: 0.3774. Min Act: -0.0002

Data Index: 372468 (C4 (Web Text))

Max Activating Token Index: 6

Text #14

Max Range: 0.4397. Min Range: -0.4397

Max Act: 0.3539. Min Act: -0.0002

Data Index: 361235 (C4 (Web Text))

Max Activating Token Index: 721

Text #15

Max Range: 0.4397. Min Range: -0.4397

Max Act: 0.3667. Min Act: -0.0002

Data Index: 577220 (C4 (Web Text))

Max Activating Token Index: 58

Text #16

Max Range: 0.4397. Min Range: -0.4397

Max Act: 0.3841. Min Act: -0.0002

Data Index: 1261095 (C4 (Web Text))

Max Activating Token Index: 18

Text #17

Max Range: 0.4397. Min Range: -0.4397

Max Act: 0.3412. Min Act: -0.0002

Data Index: 170857 (C4 (Web Text))

Max Activating Token Index: 14

Text #18

Max Range: 0.4397. Min Range: -0.4397

Max Act: 0.3332. Min Act: -0.0002

Data Index: 1252016 (C4 (Web Text))

Max Activating Token Index: 176

Text #19

Max Range: 0.4397. Min Range: -0.4397

Max Act: 0.3395. Min Act: -0.0002

Data Index: 1009779 (C4 (Web Text))

Max Activating Token Index: 904