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

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

Neuron 5074 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: 0.0551. Min Range: -0.0551

Max Act: 0.0551. Min Act: -0.0001

Data Index: 297091 (C4 (Web Text))

Max Activating Token Index: 482

Text #1

Max Range: 0.0551. Min Range: -0.0551

Max Act: 0.0444. Min Act: -0.0000

Data Index: 253501 (C4 (Web Text))

Max Activating Token Index: 719

Text #2

Max Range: 0.0551. Min Range: -0.0551

Max Act: 0.0454. Min Act: -0.0001

Data Index: 537050 (C4 (Web Text))

Max Activating Token Index: 178

Text #3

Max Range: 0.0551. Min Range: -0.0551

Max Act: 0.0400. Min Act: -0.0001

Data Index: 270416 (C4 (Web Text))

Max Activating Token Index: 45

Text #4

Max Range: 0.0551. Min Range: -0.0551

Max Act: 0.0420. Min Act: -0.0001

Data Index: 134814 (C4 (Web Text))

Max Activating Token Index: 382

Text #5

Max Range: 0.0551. Min Range: -0.0551

Max Act: 0.0405. Min Act: -0.0000

Data Index: 1258846 (C4 (Web Text))

Max Activating Token Index: 666

Text #6

Max Range: 0.0551. Min Range: -0.0551

Max Act: 0.0386. Min Act: -0.0000

Data Index: 1214164 (C4 (Web Text))

Max Activating Token Index: 909

Text #7

Max Range: 0.0551. Min Range: -0.0551

Max Act: 0.0395. Min Act: -0.0000

Data Index: 167089 (C4 (Web Text))

Max Activating Token Index: 89

Text #8

Max Range: 0.0551. Min Range: -0.0551

Max Act: 0.0392. Min Act: -0.0001

Data Index: 642621 (C4 (Web Text))

Max Activating Token Index: 41

Text #9

Max Range: 0.0551. Min Range: -0.0551

Max Act: 0.0397. Min Act: -0.0001

Data Index: 855238 (C4 (Web Text))

Max Activating Token Index: 893

Text #10

Max Range: 0.0551. Min Range: -0.0551

Max Act: 0.0417. Min Act: -0.0000

Data Index: 796412 (C4 (Web Text))

Max Activating Token Index: 547

Text #11

Max Range: 0.0551. Min Range: -0.0551

Max Act: 0.0382. Min Act: -0.0001

Data Index: 718341 (C4 (Web Text))

Max Activating Token Index: 12

Text #12

Max Range: 0.0551. Min Range: -0.0551

Max Act: 0.0326. Min Act: -0.0001

Data Index: 1175409 (C4 (Web Text))

Max Activating Token Index: 67

Text #13

Max Range: 0.0551. Min Range: -0.0551

Max Act: 0.0404. Min Act: -0.0000

Data Index: 768399 (C4 (Web Text))

Max Activating Token Index: 919

Text #14

Max Range: 0.0551. Min Range: -0.0551

Max Act: 0.0343. Min Act: -0.0001

Data Index: 685174 (C4 (Web Text))

Max Activating Token Index: 969

Text #15

Max Range: 0.0551. Min Range: -0.0551

Max Act: 0.0362. Min Act: -0.0001

Data Index: 1140223 (C4 (Web Text))

Max Activating Token Index: 866

Text #16

Max Range: 0.0551. Min Range: -0.0551

Max Act: 0.0369. Min Act: -0.0000

Data Index: 153278 (C4 (Web Text))

Max Activating Token Index: 776

Text #17

Max Range: 0.0551. Min Range: -0.0551

Max Act: 0.0366. Min Act: -0.0000

Data Index: 532983 (C4 (Web Text))

Max Activating Token Index: 200

Text #18

Max Range: 0.0551. Min Range: -0.0551

Max Act: 0.0312. Min Act: -0.0000

Data Index: 1351263 (C4 (Web Text))

Max Activating Token Index: 716

Text #19

Max Range: 0.0551. Min Range: -0.0551

Max Act: 0.0360. Min Act: -0.0000

Data Index: 1275655 (C4 (Web Text))

Max Activating Token Index: 240