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

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

Neuron 4688 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: 0.4382. Min Range: -0.4382

Max Act: 0.4247. Min Act: -0.0000

Data Index: 298691 (C4 (Web Text))

Max Activating Token Index: 128

Text #1

Max Range: 0.4382. Min Range: -0.4382

Max Act: 0.4382. Min Act: -0.0000

Data Index: 1148688 (C4 (Web Text))

Max Activating Token Index: 758

Text #2

Max Range: 0.4382. Min Range: -0.4382

Max Act: 0.4351. Min Act: -0.0000

Data Index: 240020 (C4 (Web Text))

Max Activating Token Index: 208

Text #3

Max Range: 0.4382. Min Range: -0.4382

Max Act: 0.4288. Min Act: -0.0000

Data Index: 242617 (C4 (Web Text))

Max Activating Token Index: 268

Text #4

Max Range: 0.4382. Min Range: -0.4382

Max Act: 0.3615. Min Act: -0.0000

Data Index: 371513 (C4 (Web Text))

Max Activating Token Index: 508

Text #5

Max Range: 0.4382. Min Range: -0.4382

Max Act: 0.3517. Min Act: -0.0000

Data Index: 699088 (C4 (Web Text))

Max Activating Token Index: 974

Text #6

Max Range: 0.4382. Min Range: -0.4382

Max Act: 0.3669. Min Act: -0.0000

Data Index: 1029919 (C4 (Web Text))

Max Activating Token Index: 507

Text #7

Max Range: 0.4382. Min Range: -0.4382

Max Act: 0.3651. Min Act: -0.0000

Data Index: 818586 (C4 (Web Text))

Max Activating Token Index: 89

Text #8

Max Range: 0.4382. Min Range: -0.4382

Max Act: 0.3537. Min Act: -0.0000

Data Index: 1098226 (C4 (Web Text))

Max Activating Token Index: 136

Text #9

Max Range: 0.4382. Min Range: -0.4382

Max Act: 0.3481. Min Act: -0.0000

Data Index: 356046 (C4 (Web Text))

Max Activating Token Index: 102

Text #10

Max Range: 0.4382. Min Range: -0.4382

Max Act: 0.3699. Min Act: -0.0000

Data Index: 494884 (C4 (Web Text))

Max Activating Token Index: 1013

Text #11

Max Range: 0.4382. Min Range: -0.4382

Max Act: 0.3475. Min Act: -0.0000

Data Index: 1186179 (C4 (Web Text))

Max Activating Token Index: 1011

Text #12

Max Range: 0.4382. Min Range: -0.4382

Max Act: 0.3304. Min Act: -0.0000

Data Index: 691285 (C4 (Web Text))

Max Activating Token Index: 298

Text #13

Max Range: 0.4382. Min Range: -0.4382

Max Act: 0.3217. Min Act: -0.0000

Data Index: 1057851 (C4 (Web Text))

Max Activating Token Index: 235

Text #14

Max Range: 0.4382. Min Range: -0.4382

Max Act: 0.3504. Min Act: -0.0000

Data Index: 1033060 (C4 (Web Text))

Max Activating Token Index: 228

Text #15

Max Range: 0.4382. Min Range: -0.4382

Max Act: 0.2971. Min Act: -0.0000

Data Index: 1011849 (C4 (Web Text))

Max Activating Token Index: 592

Text #16

Max Range: 0.4382. Min Range: -0.4382

Max Act: 0.3414. Min Act: -0.0000

Data Index: 241705 (C4 (Web Text))

Max Activating Token Index: 369

Text #17

Max Range: 0.4382. Min Range: -0.4382

Max Act: 0.3258. Min Act: -0.0000

Data Index: 79951 (C4 (Web Text))

Max Activating Token Index: 779

Text #18

Max Range: 0.4382. Min Range: -0.4382

Max Act: 0.3134. Min Act: -0.0000

Data Index: 118725 (C4 (Web Text))

Max Activating Token Index: 80

Text #19

Max Range: 0.4382. Min Range: -0.4382

Max Act: 0.3433. Min Act: -0.0000

Data Index: 952212 (C4 (Web Text))

Max Activating Token Index: 120