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

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

Neuron 665 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 3.0875. Min Range: -3.0875

Max Act: 3.0875. Min Act: -0.0001

Data Index: 11687 (C4 (Web Text))

Max Activating Token Index: 31

Text #1

Max Range: 3.0875. Min Range: -3.0875

Max Act: 2.4603. Min Act: -0.0001

Data Index: 266973 (C4 (Web Text))

Max Activating Token Index: 979

Text #2

Max Range: 3.0875. Min Range: -3.0875

Max Act: 2.4466. Min Act: -0.0001

Data Index: 201236 (C4 (Web Text))

Max Activating Token Index: 222

Text #3

Max Range: 3.0875. Min Range: -3.0875

Max Act: 2.2114. Min Act: -0.0001

Data Index: 1226978 (C4 (Web Text))

Max Activating Token Index: 411

Text #4

Max Range: 3.0875. Min Range: -3.0875

Max Act: 2.1190. Min Act: -0.0000

Data Index: 421695 (C4 (Web Text))

Max Activating Token Index: 299

Text #5

Max Range: 3.0875. Min Range: -3.0875

Max Act: 2.0892. Min Act: -0.0001

Data Index: 241436 (C4 (Web Text))

Max Activating Token Index: 271

Text #6

Max Range: 3.0875. Min Range: -3.0875

Max Act: 1.9816. Min Act: -0.0001

Data Index: 516826 (C4 (Web Text))

Max Activating Token Index: 453

Text #7

Max Range: 3.0875. Min Range: -3.0875

Max Act: 2.0952. Min Act: -0.0001

Data Index: 380350 (C4 (Web Text))

Max Activating Token Index: 675

Text #8

Max Range: 3.0875. Min Range: -3.0875

Max Act: 1.9081. Min Act: -0.0001

Data Index: 732675 (C4 (Web Text))

Max Activating Token Index: 107

Text #9

Max Range: 3.0875. Min Range: -3.0875

Max Act: 1.8489. Min Act: -0.0000

Data Index: 767280 (C4 (Web Text))

Max Activating Token Index: 710

Text #10

Max Range: 3.0875. Min Range: -3.0875

Max Act: 1.7972. Min Act: -0.0001

Data Index: 494871 (C4 (Web Text))

Max Activating Token Index: 701

Text #11

Max Range: 3.0875. Min Range: -3.0875

Max Act: 1.8739. Min Act: -0.0001

Data Index: 399181 (C4 (Web Text))

Max Activating Token Index: 717

Text #12

Max Range: 3.0875. Min Range: -3.0875

Max Act: 1.7450. Min Act: -0.0001

Data Index: 1123854 (C4 (Web Text))

Max Activating Token Index: 199

Text #13

Max Range: 3.0875. Min Range: -3.0875

Max Act: 1.6797. Min Act: -0.0001

Data Index: 933816 (C4 (Web Text))

Max Activating Token Index: 27

Text #14

Max Range: 3.0875. Min Range: -3.0875

Max Act: 1.8667. Min Act: -0.0001

Data Index: 980893 (C4 (Web Text))

Max Activating Token Index: 98

Text #15

Max Range: 3.0875. Min Range: -3.0875

Max Act: 1.6397. Min Act: -0.0001

Data Index: 1068685 (C4 (Web Text))

Max Activating Token Index: 373

Text #16

Max Range: 3.0875. Min Range: -3.0875

Max Act: 1.6994. Min Act: -0.0001

Data Index: 134029 (C4 (Web Text))

Max Activating Token Index: 306

Text #17

Max Range: 3.0875. Min Range: -3.0875

Max Act: 1.6219. Min Act: -0.0001

Data Index: 999354 (C4 (Web Text))

Max Activating Token Index: 553

Text #18

Max Range: 3.0875. Min Range: -3.0875

Max Act: 1.5638. Min Act: -0.0001

Data Index: 438334 (C4 (Web Text))

Max Activating Token Index: 22

Text #19

Max Range: 3.0875. Min Range: -3.0875

Max Act: 1.7362. Min Act: -0.0001

Data Index: 279537 (C4 (Web Text))

Max Activating Token Index: 604