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

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

Neuron 1876 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1973. Min Range: -0.1973

Max Act: 0.1939. Min Act: -0.0001

Data Index: 927207 (C4 (Web Text))

Max Activating Token Index: 832

Text #1

Max Range: 0.1973. Min Range: -0.1973

Max Act: 0.1890. Min Act: -0.0001

Data Index: 811482 (C4 (Web Text))

Max Activating Token Index: 790

Text #2

Max Range: 0.1973. Min Range: -0.1973

Max Act: 0.1973. Min Act: -0.0001

Data Index: 674754 (C4 (Web Text))

Max Activating Token Index: 432

Text #3

Max Range: 0.1973. Min Range: -0.1973

Max Act: 0.1666. Min Act: -0.0001

Data Index: 822605 (C4 (Web Text))

Max Activating Token Index: 504

Text #4

Max Range: 0.1973. Min Range: -0.1973

Max Act: 0.1669. Min Act: -0.0001

Data Index: 1029229 (C4 (Web Text))

Max Activating Token Index: 400

Text #5

Max Range: 0.1973. Min Range: -0.1973

Max Act: 0.1422. Min Act: -0.0001

Data Index: 386109 (C4 (Web Text))

Max Activating Token Index: 200

Text #6

Max Range: 0.1973. Min Range: -0.1973

Max Act: 0.1612. Min Act: -0.0001

Data Index: 608573 (C4 (Web Text))

Max Activating Token Index: 278

Text #7

Max Range: 0.1973. Min Range: -0.1973

Max Act: 0.1563. Min Act: -0.0001

Data Index: 1349397 (C4 (Web Text))

Max Activating Token Index: 413

Text #8

Max Range: 0.1973. Min Range: -0.1973

Max Act: 0.1574. Min Act: -0.0001

Data Index: 412156 (C4 (Web Text))

Max Activating Token Index: 377

Text #9

Max Range: 0.1973. Min Range: -0.1973

Max Act: 0.1595. Min Act: -0.0001

Data Index: 1297346 (C4 (Web Text))

Max Activating Token Index: 244

Text #10

Max Range: 0.1973. Min Range: -0.1973

Max Act: 0.1597. Min Act: -0.0001

Data Index: 585451 (C4 (Web Text))

Max Activating Token Index: 270

Text #11

Max Range: 0.1973. Min Range: -0.1973

Max Act: 0.1541. Min Act: -0.0001

Data Index: 808163 (C4 (Web Text))

Max Activating Token Index: 87

Text #12

Max Range: 0.1973. Min Range: -0.1973

Max Act: 0.1594. Min Act: -0.0001

Data Index: 1252476 (C4 (Web Text))

Max Activating Token Index: 858

Text #13

Max Range: 0.1973. Min Range: -0.1973

Max Act: 0.1588. Min Act: -0.0001

Data Index: 390921 (C4 (Web Text))

Max Activating Token Index: 108

Text #14

Max Range: 0.1973. Min Range: -0.1973

Max Act: 0.1549. Min Act: -0.0001

Data Index: 377092 (C4 (Web Text))

Max Activating Token Index: 295

Text #15

Max Range: 0.1973. Min Range: -0.1973

Max Act: 0.1503. Min Act: -0.0001

Data Index: 785361 (C4 (Web Text))

Max Activating Token Index: 309

Text #16

Max Range: 0.1973. Min Range: -0.1973

Max Act: 0.1568. Min Act: -0.0001

Data Index: 131136 (C4 (Web Text))

Max Activating Token Index: 371

Text #17

Max Range: 0.1973. Min Range: -0.1973

Max Act: 0.1502. Min Act: -0.0001

Data Index: 486153 (C4 (Web Text))

Max Activating Token Index: 466

Text #18

Max Range: 0.1973. Min Range: -0.1973

Max Act: 0.1495. Min Act: -0.0001

Data Index: 751751 (C4 (Web Text))

Max Activating Token Index: 278

Text #19

Max Range: 0.1973. Min Range: -0.1973

Max Act: 0.1454. Min Act: -0.0001

Data Index: 711027 (C4 (Web Text))

Max Activating Token Index: 325