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

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

Neuron 2891 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.1426. Min Range: -1.1426

Max Act: 1.1426. Min Act: -0.0001

Data Index: 310833 (C4 (Web Text))

Max Activating Token Index: 605

Text #1

Max Range: 1.1426. Min Range: -1.1426

Max Act: 1.0412. Min Act: -0.0001

Data Index: 924902 (C4 (Web Text))

Max Activating Token Index: 874

Text #2

Max Range: 1.1426. Min Range: -1.1426

Max Act: 1.0082. Min Act: -0.0001

Data Index: 325828 (C4 (Web Text))

Max Activating Token Index: 988

Text #3

Max Range: 1.1426. Min Range: -1.1426

Max Act: 0.9884. Min Act: -0.0001

Data Index: 1060129 (C4 (Web Text))

Max Activating Token Index: 1005

Text #4

Max Range: 1.1426. Min Range: -1.1426

Max Act: 0.9859. Min Act: -0.0001

Data Index: 131850 (C4 (Web Text))

Max Activating Token Index: 953

Text #5

Max Range: 1.1426. Min Range: -1.1426

Max Act: 0.9368. Min Act: -0.0001

Data Index: 271122 (C4 (Web Text))

Max Activating Token Index: 67

Text #6

Max Range: 1.1426. Min Range: -1.1426

Max Act: 0.9624. Min Act: -0.0001

Data Index: 959624 (C4 (Web Text))

Max Activating Token Index: 593

Text #7

Max Range: 1.1426. Min Range: -1.1426

Max Act: 0.8899. Min Act: -0.0001

Data Index: 402515 (C4 (Web Text))

Max Activating Token Index: 987

Text #8

Max Range: 1.1426. Min Range: -1.1426

Max Act: 0.8785. Min Act: -0.0001

Data Index: 1267739 (C4 (Web Text))

Max Activating Token Index: 1000

Text #9

Max Range: 1.1426. Min Range: -1.1426

Max Act: 0.9020. Min Act: -0.0001

Data Index: 536937 (C4 (Web Text))

Max Activating Token Index: 55

Text #10

Max Range: 1.1426. Min Range: -1.1426

Max Act: 0.8744. Min Act: -0.0001

Data Index: 1248218 (C4 (Web Text))

Max Activating Token Index: 991

Text #11

Max Range: 1.1426. Min Range: -1.1426

Max Act: 0.9187. Min Act: -0.0001

Data Index: 1133243 (C4 (Web Text))

Max Activating Token Index: 299

Text #12

Max Range: 1.1426. Min Range: -1.1426

Max Act: 0.8875. Min Act: -0.0001

Data Index: 384547 (C4 (Web Text))

Max Activating Token Index: 223

Text #13

Max Range: 1.1426. Min Range: -1.1426

Max Act: 0.8337. Min Act: -0.0001

Data Index: 796817 (C4 (Web Text))

Max Activating Token Index: 375

Text #14

Max Range: 1.1426. Min Range: -1.1426

Max Act: 0.8749. Min Act: -0.0001

Data Index: 493282 (C4 (Web Text))

Max Activating Token Index: 85

Text #15

Max Range: 1.1426. Min Range: -1.1426

Max Act: 0.8388. Min Act: -0.0001

Data Index: 61019 (C4 (Web Text))

Max Activating Token Index: 856

Text #16

Max Range: 1.1426. Min Range: -1.1426

Max Act: 0.8332. Min Act: -0.0001

Data Index: 1520260 (Python Code)

Max Activating Token Index: 378

Text #17

Max Range: 1.1426. Min Range: -1.1426

Max Act: 0.8546. Min Act: -0.0001

Data Index: 268912 (C4 (Web Text))

Max Activating Token Index: 437

Text #18

Max Range: 1.1426. Min Range: -1.1426

Max Act: 0.8895. Min Act: -0.0001

Data Index: 914705 (C4 (Web Text))

Max Activating Token Index: 851

Text #19

Max Range: 1.1426. Min Range: -1.1426

Max Act: 0.8512. Min Act: -0.0001

Data Index: 823073 (C4 (Web Text))

Max Activating Token Index: 965