Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 5489 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.0527. Min Range: -0.0527

Max Act: 0.0527. Min Act: -0.0001

Data Index: 515343 (C4 (Web Text))

Max Activating Token Index: 647

Text #1

Max Range: 0.0527. Min Range: -0.0527

Max Act: 0.0379. Min Act: -0.0001

Data Index: 335219 (C4 (Web Text))

Max Activating Token Index: 988

Text #2

Max Range: 0.0527. Min Range: -0.0527

Max Act: 0.0305. Min Act: -0.0001

Data Index: 991092 (C4 (Web Text))

Max Activating Token Index: 935

Text #3

Max Range: 0.0527. Min Range: -0.0527

Max Act: 0.0317. Min Act: -0.0001

Data Index: 1165696 (C4 (Web Text))

Max Activating Token Index: 271

Text #4

Max Range: 0.0527. Min Range: -0.0527

Max Act: 0.0270. Min Act: -0.0001

Data Index: 1397631 (Python Code)

Max Activating Token Index: 256

Text #5

Max Range: 0.0527. Min Range: -0.0527

Max Act: 0.0322. Min Act: -0.0001

Data Index: 1463605 (Python Code)

Max Activating Token Index: 251

Text #6

Max Range: 0.0527. Min Range: -0.0527

Max Act: 0.0314. Min Act: -0.0001

Data Index: 1366877 (Python Code)

Max Activating Token Index: 65

Text #7

Max Range: 0.0527. Min Range: -0.0527

Max Act: 0.0312. Min Act: -0.0001

Data Index: 122281 (C4 (Web Text))

Max Activating Token Index: 870

Text #8

Max Range: 0.0527. Min Range: -0.0527

Max Act: 0.0265. Min Act: -0.0001

Data Index: 1620265 (Python Code)

Max Activating Token Index: 505

Text #9

Max Range: 0.0527. Min Range: -0.0527

Max Act: 0.0285. Min Act: -0.0001

Data Index: 1329908 (C4 (Web Text))

Max Activating Token Index: 350

Text #10

Max Range: 0.0527. Min Range: -0.0527

Max Act: 0.0270. Min Act: -0.0001

Data Index: 464174 (C4 (Web Text))

Max Activating Token Index: 66

Text #11

Max Range: 0.0527. Min Range: -0.0527

Max Act: 0.0267. Min Act: -0.0001

Data Index: 698483 (C4 (Web Text))

Max Activating Token Index: 671

Text #12

Max Range: 0.0527. Min Range: -0.0527

Max Act: 0.0306. Min Act: -0.0001

Data Index: 1543347 (Python Code)

Max Activating Token Index: 453

Text #13

Max Range: 0.0527. Min Range: -0.0527

Max Act: 0.0273. Min Act: -0.0001

Data Index: 214742 (C4 (Web Text))

Max Activating Token Index: 658

Text #14

Max Range: 0.0527. Min Range: -0.0527

Max Act: 0.0272. Min Act: -0.0001

Data Index: 1575195 (Python Code)

Max Activating Token Index: 784

Text #15

Max Range: 0.0527. Min Range: -0.0527

Max Act: 0.0262. Min Act: -0.0001

Data Index: 1599329 (Python Code)

Max Activating Token Index: 872

Text #16

Max Range: 0.0527. Min Range: -0.0527

Max Act: 0.0231. Min Act: -0.0001

Data Index: 288686 (C4 (Web Text))

Max Activating Token Index: 894

Text #17

Max Range: 0.0527. Min Range: -0.0527

Max Act: 0.0230. Min Act: -0.0001

Data Index: 1538119 (Python Code)

Max Activating Token Index: 721

Text #18

Max Range: 0.0527. Min Range: -0.0527

Max Act: 0.0263. Min Act: -0.0001

Data Index: 58144 (C4 (Web Text))

Max Activating Token Index: 478

Text #19

Max Range: 0.0527. Min Range: -0.0527

Max Act: 0.0262. Min Act: -0.0001

Data Index: 586054 (C4 (Web Text))

Max Activating Token Index: 838