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

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

Neuron 4496 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.3699. Min Range: -2.3699

Max Act: 2.3699. Min Act: -0.0000

Data Index: 1045019 (C4 (Web Text))

Max Activating Token Index: 543

Text #1

Max Range: 2.3699. Min Range: -2.3699

Max Act: 2.3367. Min Act: -0.0000

Data Index: 1355015 (C4 (Web Text))

Max Activating Token Index: 388

Text #2

Max Range: 2.3699. Min Range: -2.3699

Max Act: 2.3244. Min Act: -0.0000

Data Index: 333953 (C4 (Web Text))

Max Activating Token Index: 646

Text #3

Max Range: 2.3699. Min Range: -2.3699

Max Act: 2.0328. Min Act: -0.0000

Data Index: 124622 (C4 (Web Text))

Max Activating Token Index: 340

Text #4

Max Range: 2.3699. Min Range: -2.3699

Max Act: 2.1565. Min Act: -0.0000

Data Index: 918317 (C4 (Web Text))

Max Activating Token Index: 770

Text #5

Max Range: 2.3699. Min Range: -2.3699

Max Act: 2.1366. Min Act: -0.0000

Data Index: 660486 (C4 (Web Text))

Max Activating Token Index: 74

Text #6

Max Range: 2.3699. Min Range: -2.3699

Max Act: 2.0960. Min Act: -0.0000

Data Index: 128343 (C4 (Web Text))

Max Activating Token Index: 232

Text #7

Max Range: 2.3699. Min Range: -2.3699

Max Act: 2.1191. Min Act: -0.0000

Data Index: 877773 (C4 (Web Text))

Max Activating Token Index: 783

Text #8

Max Range: 2.3699. Min Range: -2.3699

Max Act: 2.1082. Min Act: -0.0000

Data Index: 936679 (C4 (Web Text))

Max Activating Token Index: 781

Text #9

Max Range: 2.3699. Min Range: -2.3699

Max Act: 2.0940. Min Act: -0.0000

Data Index: 1113759 (C4 (Web Text))

Max Activating Token Index: 594

Text #10

Max Range: 2.3699. Min Range: -2.3699

Max Act: 2.0862. Min Act: -0.0000

Data Index: 1224033 (C4 (Web Text))

Max Activating Token Index: 933

Text #11

Max Range: 2.3699. Min Range: -2.3699

Max Act: 1.9457. Min Act: -0.0000

Data Index: 220507 (C4 (Web Text))

Max Activating Token Index: 648

Text #12

Max Range: 2.3699. Min Range: -2.3699

Max Act: 1.9118. Min Act: -0.0000

Data Index: 56191 (C4 (Web Text))

Max Activating Token Index: 179

Text #13

Max Range: 2.3699. Min Range: -2.3699

Max Act: 2.0133. Min Act: -0.0000

Data Index: 393215 (C4 (Web Text))

Max Activating Token Index: 394

Text #14

Max Range: 2.3699. Min Range: -2.3699

Max Act: 2.1316. Min Act: -0.0000

Data Index: 1337492 (C4 (Web Text))

Max Activating Token Index: 545

Text #15

Max Range: 2.3699. Min Range: -2.3699

Max Act: 1.9865. Min Act: -0.0000

Data Index: 920091 (C4 (Web Text))

Max Activating Token Index: 458

Text #16

Max Range: 2.3699. Min Range: -2.3699

Max Act: 1.9444. Min Act: -0.0000

Data Index: 335902 (C4 (Web Text))

Max Activating Token Index: 123

Text #17

Max Range: 2.3699. Min Range: -2.3699

Max Act: 1.9317. Min Act: -0.0000

Data Index: 58049 (C4 (Web Text))

Max Activating Token Index: 369

Text #18

Max Range: 2.3699. Min Range: -2.3699

Max Act: 1.9201. Min Act: -0.0000

Data Index: 323970 (C4 (Web Text))

Max Activating Token Index: 455

Text #19

Max Range: 2.3699. Min Range: -2.3699

Max Act: 1.9156. Min Act: -0.0000

Data Index: 735664 (C4 (Web Text))

Max Activating Token Index: 531