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

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

Neuron 3882 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 1.1369. Min Range: -1.1369

Max Act: 1.1369. Min Act: -0.0000

Data Index: 463981 (C4 (Web Text))

Max Activating Token Index: 220

Text #1

Max Range: 1.1369. Min Range: -1.1369

Max Act: 1.0286. Min Act: -0.0000

Data Index: 1025215 (C4 (Web Text))

Max Activating Token Index: 370

Text #2

Max Range: 1.1369. Min Range: -1.1369

Max Act: 0.9160. Min Act: -0.0000

Data Index: 31775 (C4 (Web Text))

Max Activating Token Index: 21

Text #3

Max Range: 1.1369. Min Range: -1.1369

Max Act: 0.7211. Min Act: -0.0000

Data Index: 959505 (C4 (Web Text))

Max Activating Token Index: 682

Text #4

Max Range: 1.1369. Min Range: -1.1369

Max Act: 0.6858. Min Act: -0.0000

Data Index: 962642 (C4 (Web Text))

Max Activating Token Index: 208

Text #5

Max Range: 1.1369. Min Range: -1.1369

Max Act: 0.7699. Min Act: -0.0000

Data Index: 680992 (C4 (Web Text))

Max Activating Token Index: 105

Text #6

Max Range: 1.1369. Min Range: -1.1369

Max Act: 0.6901. Min Act: -0.0000

Data Index: 1120274 (C4 (Web Text))

Max Activating Token Index: 225

Text #7

Max Range: 1.1369. Min Range: -1.1369

Max Act: 0.6383. Min Act: -0.0000

Data Index: 979683 (C4 (Web Text))

Max Activating Token Index: 610

Text #8

Max Range: 1.1369. Min Range: -1.1369

Max Act: 0.7200. Min Act: -0.0000

Data Index: 707037 (C4 (Web Text))

Max Activating Token Index: 928

Text #9

Max Range: 1.1369. Min Range: -1.1369

Max Act: 0.6765. Min Act: -0.0000

Data Index: 165761 (C4 (Web Text))

Max Activating Token Index: 206

Text #10

Max Range: 1.1369. Min Range: -1.1369

Max Act: 0.6882. Min Act: -0.0001

Data Index: 1320364 (C4 (Web Text))

Max Activating Token Index: 976

Text #11

Max Range: 1.1369. Min Range: -1.1369

Max Act: 0.6751. Min Act: -0.0000

Data Index: 954899 (C4 (Web Text))

Max Activating Token Index: 94

Text #12

Max Range: 1.1369. Min Range: -1.1369

Max Act: 0.6521. Min Act: -0.0000

Data Index: 208382 (C4 (Web Text))

Max Activating Token Index: 301

Text #13

Max Range: 1.1369. Min Range: -1.1369

Max Act: 0.6536. Min Act: -0.0001

Data Index: 511678 (C4 (Web Text))

Max Activating Token Index: 399

Text #14

Max Range: 1.1369. Min Range: -1.1369

Max Act: 0.6420. Min Act: -0.0000

Data Index: 497893 (C4 (Web Text))

Max Activating Token Index: 26

Text #15

Max Range: 1.1369. Min Range: -1.1369

Max Act: 0.6131. Min Act: -0.0000

Data Index: 140569 (C4 (Web Text))

Max Activating Token Index: 313

Text #16

Max Range: 1.1369. Min Range: -1.1369

Max Act: 0.6319. Min Act: -0.0000

Data Index: 817250 (C4 (Web Text))

Max Activating Token Index: 253

Text #17

Max Range: 1.1369. Min Range: -1.1369

Max Act: 0.6638. Min Act: -0.0000

Data Index: 472336 (C4 (Web Text))

Max Activating Token Index: 159

Text #18

Max Range: 1.1369. Min Range: -1.1369

Max Act: 0.6458. Min Act: -0.0000

Data Index: 1307448 (C4 (Web Text))

Max Activating Token Index: 676

Text #19

Max Range: 1.1369. Min Range: -1.1369

Max Act: 0.6590. Min Act: -0.0000

Data Index: 1165936 (C4 (Web Text))

Max Activating Token Index: 969