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

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

Neuron 1875 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4695. Min Range: -0.4695

Max Act: 0.4695. Min Act: -0.0000

Data Index: 293596 (C4 (Web Text))

Max Activating Token Index: 846

Text #1

Max Range: 0.4695. Min Range: -0.4695

Max Act: 0.4466. Min Act: 0.0000

Data Index: 1184345 (C4 (Web Text))

Max Activating Token Index: 469

Text #2

Max Range: 0.4695. Min Range: -0.4695

Max Act: 0.4038. Min Act: -0.0000

Data Index: 1287597 (C4 (Web Text))

Max Activating Token Index: 511

Text #3

Max Range: 0.4695. Min Range: -0.4695

Max Act: 0.3471. Min Act: -0.0000

Data Index: 1226118 (C4 (Web Text))

Max Activating Token Index: 222

Text #4

Max Range: 0.4695. Min Range: -0.4695

Max Act: 0.3457. Min Act: -0.0000

Data Index: 692453 (C4 (Web Text))

Max Activating Token Index: 764

Text #5

Max Range: 0.4695. Min Range: -0.4695

Max Act: 0.3452. Min Act: -0.0000

Data Index: 501568 (C4 (Web Text))

Max Activating Token Index: 296

Text #6

Max Range: 0.4695. Min Range: -0.4695

Max Act: 0.3471. Min Act: -0.0000

Data Index: 232454 (C4 (Web Text))

Max Activating Token Index: 528

Text #7

Max Range: 0.4695. Min Range: -0.4695

Max Act: 0.3463. Min Act: -0.0001

Data Index: 264230 (C4 (Web Text))

Max Activating Token Index: 970

Text #8

Max Range: 0.4695. Min Range: -0.4695

Max Act: 0.3351. Min Act: -0.0000

Data Index: 1033854 (C4 (Web Text))

Max Activating Token Index: 628

Text #9

Max Range: 0.4695. Min Range: -0.4695

Max Act: 0.3358. Min Act: -0.0000

Data Index: 1201984 (C4 (Web Text))

Max Activating Token Index: 1009

Text #10

Max Range: 0.4695. Min Range: -0.4695

Max Act: 0.3431. Min Act: -0.0000

Data Index: 462681 (C4 (Web Text))

Max Activating Token Index: 936

Text #11

Max Range: 0.4695. Min Range: -0.4695

Max Act: 0.3399. Min Act: -0.0000

Data Index: 1049977 (C4 (Web Text))

Max Activating Token Index: 117

Text #12

Max Range: 0.4695. Min Range: -0.4695

Max Act: 0.3271. Min Act: -0.0000

Data Index: 18502 (C4 (Web Text))

Max Activating Token Index: 857

Text #13

Max Range: 0.4695. Min Range: -0.4695

Max Act: 0.3218. Min Act: 0.0000

Data Index: 1359522 (C4 (Web Text))

Max Activating Token Index: 212

Text #14

Max Range: 0.4695. Min Range: -0.4695

Max Act: 0.3197. Min Act: -0.0000

Data Index: 385177 (C4 (Web Text))

Max Activating Token Index: 195

Text #15

Max Range: 0.4695. Min Range: -0.4695

Max Act: 0.3245. Min Act: -0.0000

Data Index: 1199156 (C4 (Web Text))

Max Activating Token Index: 452

Text #16

Max Range: 0.4695. Min Range: -0.4695

Max Act: 0.3096. Min Act: -0.0000

Data Index: 680604 (C4 (Web Text))

Max Activating Token Index: 962

Text #17

Max Range: 0.4695. Min Range: -0.4695

Max Act: 0.3132. Min Act: -0.0000

Data Index: 300774 (C4 (Web Text))

Max Activating Token Index: 84

Text #18

Max Range: 0.4695. Min Range: -0.4695

Max Act: 0.3148. Min Act: -0.0000

Data Index: 366590 (C4 (Web Text))

Max Activating Token Index: 13

Text #19

Max Range: 0.4695. Min Range: -0.4695

Max Act: 0.3027. Min Act: 0.0000

Data Index: 158043 (C4 (Web Text))

Max Activating Token Index: 153