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

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

Neuron 659 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.2764. Min Range: -1.2764

Max Act: 1.2731. Min Act: -0.0001

Data Index: 244927 (C4 (Web Text))

Max Activating Token Index: 727

Text #1

Max Range: 1.2764. Min Range: -1.2764

Max Act: 1.2764. Min Act: -0.0001

Data Index: 554023 (C4 (Web Text))

Max Activating Token Index: 526

Text #2

Max Range: 1.2764. Min Range: -1.2764

Max Act: 1.2235. Min Act: -0.0001

Data Index: 1163881 (C4 (Web Text))

Max Activating Token Index: 648

Text #3

Max Range: 1.2764. Min Range: -1.2764

Max Act: 1.1570. Min Act: -0.0001

Data Index: 1456211 (Python Code)

Max Activating Token Index: 297

Text #4

Max Range: 1.2764. Min Range: -1.2764

Max Act: 1.2536. Min Act: -0.0001

Data Index: 1437195 (Python Code)

Max Activating Token Index: 462

Text #5

Max Range: 1.2764. Min Range: -1.2764

Max Act: 1.2038. Min Act: -0.0001

Data Index: 616092 (C4 (Web Text))

Max Activating Token Index: 431

Text #6

Max Range: 1.2764. Min Range: -1.2764

Max Act: 1.1914. Min Act: -0.0001

Data Index: 1260758 (C4 (Web Text))

Max Activating Token Index: 1018

Text #7

Max Range: 1.2764. Min Range: -1.2764

Max Act: 1.1432. Min Act: -0.0001

Data Index: 507965 (C4 (Web Text))

Max Activating Token Index: 976

Text #8

Max Range: 1.2764. Min Range: -1.2764

Max Act: 1.1597. Min Act: -0.0001

Data Index: 52902 (C4 (Web Text))

Max Activating Token Index: 499

Text #9

Max Range: 1.2764. Min Range: -1.2764

Max Act: 1.1505. Min Act: -0.0001

Data Index: 1326638 (C4 (Web Text))

Max Activating Token Index: 312

Text #10

Max Range: 1.2764. Min Range: -1.2764

Max Act: 1.0924. Min Act: -0.0001

Data Index: 791659 (C4 (Web Text))

Max Activating Token Index: 691

Text #11

Max Range: 1.2764. Min Range: -1.2764

Max Act: 1.1132. Min Act: -0.0001

Data Index: 23341 (C4 (Web Text))

Max Activating Token Index: 602

Text #12

Max Range: 1.2764. Min Range: -1.2764

Max Act: 1.0461. Min Act: -0.0001

Data Index: 1192439 (C4 (Web Text))

Max Activating Token Index: 259

Text #13

Max Range: 1.2764. Min Range: -1.2764

Max Act: 1.0304. Min Act: -0.0001

Data Index: 345255 (C4 (Web Text))

Max Activating Token Index: 411

Text #14

Max Range: 1.2764. Min Range: -1.2764

Max Act: 1.0271. Min Act: -0.0001

Data Index: 485740 (C4 (Web Text))

Max Activating Token Index: 322

Text #15

Max Range: 1.2764. Min Range: -1.2764

Max Act: 1.0603. Min Act: -0.0001

Data Index: 575864 (C4 (Web Text))

Max Activating Token Index: 275

Text #16

Max Range: 1.2764. Min Range: -1.2764

Max Act: 1.0195. Min Act: -0.0001

Data Index: 781699 (C4 (Web Text))

Max Activating Token Index: 831

Text #17

Max Range: 1.2764. Min Range: -1.2764

Max Act: 1.0806. Min Act: -0.0001

Data Index: 1609765 (Python Code)

Max Activating Token Index: 509

Text #18

Max Range: 1.2764. Min Range: -1.2764

Max Act: 1.0105. Min Act: -0.0001

Data Index: 797101 (C4 (Web Text))

Max Activating Token Index: 603

Text #19

Max Range: 1.2764. Min Range: -1.2764

Max Act: 1.0030. Min Act: -0.0001

Data Index: 116877 (C4 (Web Text))

Max Activating Token Index: 381