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

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

Neuron 2887 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.2317. Min Range: -2.2317

Max Act: 2.2317. Min Act: -0.0000

Data Index: 228643 (C4 (Web Text))

Max Activating Token Index: 484

Text #1

Max Range: 2.2317. Min Range: -2.2317

Max Act: 2.0742. Min Act: -0.0000

Data Index: 80613 (C4 (Web Text))

Max Activating Token Index: 509

Text #2

Max Range: 2.2317. Min Range: -2.2317

Max Act: 1.7093. Min Act: -0.0000

Data Index: 611260 (C4 (Web Text))

Max Activating Token Index: 230

Text #3

Max Range: 2.2317. Min Range: -2.2317

Max Act: 1.6995. Min Act: -0.0000

Data Index: 1213718 (C4 (Web Text))

Max Activating Token Index: 680

Text #4

Max Range: 2.2317. Min Range: -2.2317

Max Act: 1.6394. Min Act: -0.0000

Data Index: 34896 (C4 (Web Text))

Max Activating Token Index: 408

Text #5

Max Range: 2.2317. Min Range: -2.2317

Max Act: 1.6494. Min Act: -0.0000

Data Index: 1334148 (C4 (Web Text))

Max Activating Token Index: 335

Text #6

Max Range: 2.2317. Min Range: -2.2317

Max Act: 1.5226. Min Act: -0.0000

Data Index: 1177356 (C4 (Web Text))

Max Activating Token Index: 393

Text #7

Max Range: 2.2317. Min Range: -2.2317

Max Act: 1.5695. Min Act: -0.0000

Data Index: 256029 (C4 (Web Text))

Max Activating Token Index: 178

Text #8

Max Range: 2.2317. Min Range: -2.2317

Max Act: 1.3860. Min Act: -0.0000

Data Index: 1220964 (C4 (Web Text))

Max Activating Token Index: 858

Text #9

Max Range: 2.2317. Min Range: -2.2317

Max Act: 1.3214. Min Act: -0.0000

Data Index: 1160825 (C4 (Web Text))

Max Activating Token Index: 610

Text #10

Max Range: 2.2317. Min Range: -2.2317

Max Act: 1.4201. Min Act: -0.0000

Data Index: 498181 (C4 (Web Text))

Max Activating Token Index: 522

Text #11

Max Range: 2.2317. Min Range: -2.2317

Max Act: 1.3511. Min Act: -0.0000

Data Index: 634495 (C4 (Web Text))

Max Activating Token Index: 409

Text #12

Max Range: 2.2317. Min Range: -2.2317

Max Act: 1.2973. Min Act: -0.0000

Data Index: 1157501 (C4 (Web Text))

Max Activating Token Index: 78

Text #13

Max Range: 2.2317. Min Range: -2.2317

Max Act: 1.2648. Min Act: -0.0000

Data Index: 654228 (C4 (Web Text))

Max Activating Token Index: 620

Text #14

Max Range: 2.2317. Min Range: -2.2317

Max Act: 1.2096. Min Act: -0.0000

Data Index: 14017 (C4 (Web Text))

Max Activating Token Index: 228

Text #15

Max Range: 2.2317. Min Range: -2.2317

Max Act: 1.0324. Min Act: -0.0000

Data Index: 566285 (C4 (Web Text))

Max Activating Token Index: 694

Text #16

Max Range: 2.2317. Min Range: -2.2317

Max Act: 1.1357. Min Act: -0.0000

Data Index: 637432 (C4 (Web Text))

Max Activating Token Index: 440

Text #17

Max Range: 2.2317. Min Range: -2.2317

Max Act: 1.1494. Min Act: -0.0000

Data Index: 884629 (C4 (Web Text))

Max Activating Token Index: 504

Text #18

Max Range: 2.2317. Min Range: -2.2317

Max Act: 1.1485. Min Act: -0.0000

Data Index: 1240293 (C4 (Web Text))

Max Activating Token Index: 174

Text #19

Max Range: 2.2317. Min Range: -2.2317

Max Act: 1.0943. Min Act: -0.0000

Data Index: 1324164 (C4 (Web Text))

Max Activating Token Index: 138