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

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

Neuron 3459 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: 1.5920. Min Range: -1.5920

Max Act: 1.5920. Min Act: -0.0001

Data Index: 1346928 (C4 (Web Text))

Max Activating Token Index: 745

Text #1

Max Range: 1.5920. Min Range: -1.5920

Max Act: 1.5573. Min Act: -0.0001

Data Index: 980764 (C4 (Web Text))

Max Activating Token Index: 482

Text #2

Max Range: 1.5920. Min Range: -1.5920

Max Act: 1.5407. Min Act: -0.0001

Data Index: 902425 (C4 (Web Text))

Max Activating Token Index: 503

Text #3

Max Range: 1.5920. Min Range: -1.5920

Max Act: 1.5041. Min Act: -0.0001

Data Index: 1106135 (C4 (Web Text))

Max Activating Token Index: 223

Text #4

Max Range: 1.5920. Min Range: -1.5920

Max Act: 1.5029. Min Act: -0.0001

Data Index: 1235353 (C4 (Web Text))

Max Activating Token Index: 808

Text #5

Max Range: 1.5920. Min Range: -1.5920

Max Act: 1.2945. Min Act: -0.0001

Data Index: 543310 (C4 (Web Text))

Max Activating Token Index: 659

Text #6

Max Range: 1.5920. Min Range: -1.5920

Max Act: 1.4049. Min Act: -0.0001

Data Index: 495560 (C4 (Web Text))

Max Activating Token Index: 97

Text #7

Max Range: 1.5920. Min Range: -1.5920

Max Act: 1.3324. Min Act: -0.0001

Data Index: 1058451 (C4 (Web Text))

Max Activating Token Index: 655

Text #8

Max Range: 1.5920. Min Range: -1.5920

Max Act: 1.4772. Min Act: -0.0001

Data Index: 1164206 (C4 (Web Text))

Max Activating Token Index: 494

Text #9

Max Range: 1.5920. Min Range: -1.5920

Max Act: 1.3261. Min Act: -0.0001

Data Index: 600549 (C4 (Web Text))

Max Activating Token Index: 860

Text #10

Max Range: 1.5920. Min Range: -1.5920

Max Act: 1.4530. Min Act: -0.0001

Data Index: 644893 (C4 (Web Text))

Max Activating Token Index: 485

Text #11

Max Range: 1.5920. Min Range: -1.5920

Max Act: 1.2365. Min Act: -0.0001

Data Index: 617704 (C4 (Web Text))

Max Activating Token Index: 971

Text #12

Max Range: 1.5920. Min Range: -1.5920

Max Act: 1.4375. Min Act: -0.0001

Data Index: 771820 (C4 (Web Text))

Max Activating Token Index: 936

Text #13

Max Range: 1.5920. Min Range: -1.5920

Max Act: 1.3240. Min Act: -0.0001

Data Index: 577507 (C4 (Web Text))

Max Activating Token Index: 809

Text #14

Max Range: 1.5920. Min Range: -1.5920

Max Act: 1.2447. Min Act: -0.0001

Data Index: 373082 (C4 (Web Text))

Max Activating Token Index: 1009

Text #15

Max Range: 1.5920. Min Range: -1.5920

Max Act: 1.2232. Min Act: -0.0001

Data Index: 186134 (C4 (Web Text))

Max Activating Token Index: 540

Text #16

Max Range: 1.5920. Min Range: -1.5920

Max Act: 1.3148. Min Act: -0.0001

Data Index: 123653 (C4 (Web Text))

Max Activating Token Index: 476

Text #17

Max Range: 1.5920. Min Range: -1.5920

Max Act: 1.3359. Min Act: -0.0001

Data Index: 821984 (C4 (Web Text))

Max Activating Token Index: 876

Text #18

Max Range: 1.5920. Min Range: -1.5920

Max Act: 1.3423. Min Act: -0.0001

Data Index: 1199368 (C4 (Web Text))

Max Activating Token Index: 562

Text #19

Max Range: 1.5920. Min Range: -1.5920

Max Act: 1.2702. Min Act: -0.0001

Data Index: 238958 (C4 (Web Text))

Max Activating Token Index: 100