Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 855 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 1.4428. Min Range: -1.4428

Max Act: 1.4428. Min Act: -0.0001

Data Index: 933153 (C4 (Web Text))

Max Activating Token Index: 34

Text #1

Max Range: 1.4428. Min Range: -1.4428

Max Act: 1.3595. Min Act: -0.0001

Data Index: 452490 (C4 (Web Text))

Max Activating Token Index: 284

Text #2

Max Range: 1.4428. Min Range: -1.4428

Max Act: 1.1695. Min Act: -0.0001

Data Index: 1136797 (C4 (Web Text))

Max Activating Token Index: 937

Text #3

Max Range: 1.4428. Min Range: -1.4428

Max Act: 1.0429. Min Act: -0.0001

Data Index: 527651 (C4 (Web Text))

Max Activating Token Index: 297

Text #4

Max Range: 1.4428. Min Range: -1.4428

Max Act: 1.0573. Min Act: -0.0001

Data Index: 612612 (C4 (Web Text))

Max Activating Token Index: 68

Text #5

Max Range: 1.4428. Min Range: -1.4428

Max Act: 1.1191. Min Act: -0.0001

Data Index: 789222 (C4 (Web Text))

Max Activating Token Index: 426

Text #6

Max Range: 1.4428. Min Range: -1.4428

Max Act: 1.1995. Min Act: -0.0001

Data Index: 1171834 (C4 (Web Text))

Max Activating Token Index: 737

Text #7

Max Range: 1.4428. Min Range: -1.4428

Max Act: 1.0236. Min Act: -0.0001

Data Index: 1230874 (C4 (Web Text))

Max Activating Token Index: 183

Text #8

Max Range: 1.4428. Min Range: -1.4428

Max Act: 0.9802. Min Act: -0.0001

Data Index: 427916 (C4 (Web Text))

Max Activating Token Index: 119

Text #9

Max Range: 1.4428. Min Range: -1.4428

Max Act: 1.0171. Min Act: -0.0001

Data Index: 563407 (C4 (Web Text))

Max Activating Token Index: 610

Text #10

Max Range: 1.4428. Min Range: -1.4428

Max Act: 1.0489. Min Act: -0.0001

Data Index: 428185 (C4 (Web Text))

Max Activating Token Index: 371

Text #11

Max Range: 1.4428. Min Range: -1.4428

Max Act: 0.9543. Min Act: -0.0001

Data Index: 550342 (C4 (Web Text))

Max Activating Token Index: 894

Text #12

Max Range: 1.4428. Min Range: -1.4428

Max Act: 0.9621. Min Act: -0.0001

Data Index: 510816 (C4 (Web Text))

Max Activating Token Index: 710

Text #13

Max Range: 1.4428. Min Range: -1.4428

Max Act: 0.9199. Min Act: -0.0001

Data Index: 226761 (C4 (Web Text))

Max Activating Token Index: 962

Text #14

Max Range: 1.4428. Min Range: -1.4428

Max Act: 0.9440. Min Act: -0.0001

Data Index: 1011386 (C4 (Web Text))

Max Activating Token Index: 143

Text #15

Max Range: 1.4428. Min Range: -1.4428

Max Act: 1.0257. Min Act: -0.0001

Data Index: 590244 (C4 (Web Text))

Max Activating Token Index: 62

Text #16

Max Range: 1.4428. Min Range: -1.4428

Max Act: 0.9280. Min Act: -0.0001

Data Index: 457946 (C4 (Web Text))

Max Activating Token Index: 672

Text #17

Max Range: 1.4428. Min Range: -1.4428

Max Act: 0.8647. Min Act: -0.0001

Data Index: 1217092 (C4 (Web Text))

Max Activating Token Index: 752

Text #18

Max Range: 1.4428. Min Range: -1.4428

Max Act: 0.8760. Min Act: -0.0001

Data Index: 78520 (C4 (Web Text))

Max Activating Token Index: 744

Text #19

Max Range: 1.4428. Min Range: -1.4428

Max Act: 0.8948. Min Act: -0.0001

Data Index: 575345 (C4 (Web Text))

Max Activating Token Index: 991