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

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

Neuron 998 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 7.2459. Min Range: -7.2459

Max Act: 7.2459. Min Act: -0.0001

Data Index: 1323863 (C4 (Web Text))

Max Activating Token Index: 40

Text #1

Max Range: 7.2459. Min Range: -7.2459

Max Act: 6.5535. Min Act: -0.0001

Data Index: 1316823 (C4 (Web Text))

Max Activating Token Index: 266

Text #2

Max Range: 7.2459. Min Range: -7.2459

Max Act: 6.5348. Min Act: -0.0001

Data Index: 50592 (C4 (Web Text))

Max Activating Token Index: 23

Text #3

Max Range: 7.2459. Min Range: -7.2459

Max Act: 6.3512. Min Act: -0.0001

Data Index: 141825 (C4 (Web Text))

Max Activating Token Index: 545

Text #4

Max Range: 7.2459. Min Range: -7.2459

Max Act: 6.1682. Min Act: -0.0001

Data Index: 730308 (C4 (Web Text))

Max Activating Token Index: 58

Text #5

Max Range: 7.2459. Min Range: -7.2459

Max Act: 6.2999. Min Act: -0.0001

Data Index: 1188380 (C4 (Web Text))

Max Activating Token Index: 594

Text #6

Max Range: 7.2459. Min Range: -7.2459

Max Act: 5.7834. Min Act: -0.0001

Data Index: 110531 (C4 (Web Text))

Max Activating Token Index: 21

Text #7

Max Range: 7.2459. Min Range: -7.2459

Max Act: 4.9499. Min Act: -0.0001

Data Index: 167601 (C4 (Web Text))

Max Activating Token Index: 324

Text #8

Max Range: 7.2459. Min Range: -7.2459

Max Act: 5.6012. Min Act: -0.0001

Data Index: 22303 (C4 (Web Text))

Max Activating Token Index: 987

Text #9

Max Range: 7.2459. Min Range: -7.2459

Max Act: 5.5766. Min Act: -0.0001

Data Index: 580652 (C4 (Web Text))

Max Activating Token Index: 896

Text #10

Max Range: 7.2459. Min Range: -7.2459

Max Act: 5.5443. Min Act: -0.0001

Data Index: 1026040 (C4 (Web Text))

Max Activating Token Index: 603

Text #11

Max Range: 7.2459. Min Range: -7.2459

Max Act: 5.4592. Min Act: -0.0001

Data Index: 498229 (C4 (Web Text))

Max Activating Token Index: 451

Text #12

Max Range: 7.2459. Min Range: -7.2459

Max Act: 5.4031. Min Act: -0.0001

Data Index: 1215921 (C4 (Web Text))

Max Activating Token Index: 17

Text #13

Max Range: 7.2459. Min Range: -7.2459

Max Act: 5.3795. Min Act: -0.0001

Data Index: 851360 (C4 (Web Text))

Max Activating Token Index: 23

Text #14

Max Range: 7.2459. Min Range: -7.2459

Max Act: 4.7315. Min Act: -0.0001

Data Index: 898375 (C4 (Web Text))

Max Activating Token Index: 849

Text #15

Max Range: 7.2459. Min Range: -7.2459

Max Act: 5.2692. Min Act: -0.0001

Data Index: 1089506 (C4 (Web Text))

Max Activating Token Index: 53

Text #16

Max Range: 7.2459. Min Range: -7.2459

Max Act: 5.2251. Min Act: -0.0001

Data Index: 577511 (C4 (Web Text))

Max Activating Token Index: 20

Text #17

Max Range: 7.2459. Min Range: -7.2459

Max Act: 5.1243. Min Act: -0.0001

Data Index: 1332275 (C4 (Web Text))

Max Activating Token Index: 427

Text #18

Max Range: 7.2459. Min Range: -7.2459

Max Act: 4.7125. Min Act: -0.0001

Data Index: 737892 (C4 (Web Text))

Max Activating Token Index: 304

Text #19

Max Range: 7.2459. Min Range: -7.2459

Max Act: 5.0611. Min Act: -0.0001

Data Index: 131786 (C4 (Web Text))

Max Activating Token Index: 68