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

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

Neuron 1836 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.9476. Min Range: -2.9476

Max Act: 2.9476. Min Act: -0.0000

Data Index: 171656 (C4 (Web Text))

Max Activating Token Index: 358

Text #1

Max Range: 2.9476. Min Range: -2.9476

Max Act: 2.7951. Min Act: -0.0000

Data Index: 953855 (C4 (Web Text))

Max Activating Token Index: 372

Text #2

Max Range: 2.9476. Min Range: -2.9476

Max Act: 2.7941. Min Act: -0.0000

Data Index: 29736 (C4 (Web Text))

Max Activating Token Index: 84

Text #3

Max Range: 2.9476. Min Range: -2.9476

Max Act: 2.2022. Min Act: -0.0000

Data Index: 269314 (C4 (Web Text))

Max Activating Token Index: 46

Text #4

Max Range: 2.9476. Min Range: -2.9476

Max Act: 2.2888. Min Act: -0.0000

Data Index: 953392 (C4 (Web Text))

Max Activating Token Index: 756

Text #5

Max Range: 2.9476. Min Range: -2.9476

Max Act: 2.2493. Min Act: -0.0000

Data Index: 960461 (C4 (Web Text))

Max Activating Token Index: 27

Text #6

Max Range: 2.9476. Min Range: -2.9476

Max Act: 2.1835. Min Act: -0.0000

Data Index: 97347 (C4 (Web Text))

Max Activating Token Index: 222

Text #7

Max Range: 2.9476. Min Range: -2.9476

Max Act: 2.2759. Min Act: -0.0000

Data Index: 1310829 (C4 (Web Text))

Max Activating Token Index: 749

Text #8

Max Range: 2.9476. Min Range: -2.9476

Max Act: 2.1458. Min Act: -0.0000

Data Index: 782310 (C4 (Web Text))

Max Activating Token Index: 507

Text #9

Max Range: 2.9476. Min Range: -2.9476

Max Act: 2.1015. Min Act: -0.0000

Data Index: 427758 (C4 (Web Text))

Max Activating Token Index: 43

Text #10

Max Range: 2.9476. Min Range: -2.9476

Max Act: 2.0145. Min Act: -0.0000

Data Index: 1029584 (C4 (Web Text))

Max Activating Token Index: 321

Text #11

Max Range: 2.9476. Min Range: -2.9476

Max Act: 2.2340. Min Act: -0.0000

Data Index: 1114355 (C4 (Web Text))

Max Activating Token Index: 26

Text #12

Max Range: 2.9476. Min Range: -2.9476

Max Act: 2.1188. Min Act: -0.0000

Data Index: 514417 (C4 (Web Text))

Max Activating Token Index: 824

Text #13

Max Range: 2.9476. Min Range: -2.9476

Max Act: 1.9798. Min Act: -0.0000

Data Index: 811950 (C4 (Web Text))

Max Activating Token Index: 985

Text #14

Max Range: 2.9476. Min Range: -2.9476

Max Act: 1.8672. Min Act: -0.0000

Data Index: 855270 (C4 (Web Text))

Max Activating Token Index: 934

Text #15

Max Range: 2.9476. Min Range: -2.9476

Max Act: 1.9656. Min Act: -0.0000

Data Index: 688141 (C4 (Web Text))

Max Activating Token Index: 1022

Text #16

Max Range: 2.9476. Min Range: -2.9476

Max Act: 2.0624. Min Act: -0.0000

Data Index: 838729 (C4 (Web Text))

Max Activating Token Index: 161

Text #17

Max Range: 2.9476. Min Range: -2.9476

Max Act: 1.9442. Min Act: -0.0000

Data Index: 1208673 (C4 (Web Text))

Max Activating Token Index: 514

Text #18

Max Range: 2.9476. Min Range: -2.9476

Max Act: 1.7953. Min Act: -0.0000

Data Index: 835873 (C4 (Web Text))

Max Activating Token Index: 1003

Text #19

Max Range: 2.9476. Min Range: -2.9476

Max Act: 1.9970. Min Act: -0.0000

Data Index: 1129332 (C4 (Web Text))

Max Activating Token Index: 800