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

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

Neuron 836 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.1594. Min Range: -0.1594

Max Act: 0.1552. Min Act: -0.0001

Data Index: 104895 (C4 (Web Text))

Max Activating Token Index: 111

Text #1

Max Range: 0.1594. Min Range: -0.1594

Max Act: 0.1469. Min Act: -0.0001

Data Index: 622083 (C4 (Web Text))

Max Activating Token Index: 1013

Text #2

Max Range: 0.1594. Min Range: -0.1594

Max Act: 0.1594. Min Act: -0.0001

Data Index: 1199708 (C4 (Web Text))

Max Activating Token Index: 379

Text #3

Max Range: 0.1594. Min Range: -0.1594

Max Act: 0.1480. Min Act: -0.0001

Data Index: 373222 (C4 (Web Text))

Max Activating Token Index: 62

Text #4

Max Range: 0.1594. Min Range: -0.1594

Max Act: 0.1586. Min Act: -0.0001

Data Index: 889907 (C4 (Web Text))

Max Activating Token Index: 409

Text #5

Max Range: 0.1594. Min Range: -0.1594

Max Act: 0.1442. Min Act: -0.0001

Data Index: 1322790 (C4 (Web Text))

Max Activating Token Index: 153

Text #6

Max Range: 0.1594. Min Range: -0.1594

Max Act: 0.1570. Min Act: -0.0001

Data Index: 1358260 (C4 (Web Text))

Max Activating Token Index: 485

Text #7

Max Range: 0.1594. Min Range: -0.1594

Max Act: 0.1521. Min Act: -0.0001

Data Index: 1110511 (C4 (Web Text))

Max Activating Token Index: 661

Text #8

Max Range: 0.1594. Min Range: -0.1594

Max Act: 0.1439. Min Act: -0.0001

Data Index: 607960 (C4 (Web Text))

Max Activating Token Index: 373

Text #9

Max Range: 0.1594. Min Range: -0.1594

Max Act: 0.1392. Min Act: -0.0001

Data Index: 387607 (C4 (Web Text))

Max Activating Token Index: 339

Text #10

Max Range: 0.1594. Min Range: -0.1594

Max Act: 0.1327. Min Act: -0.0001

Data Index: 838993 (C4 (Web Text))

Max Activating Token Index: 615

Text #11

Max Range: 0.1594. Min Range: -0.1594

Max Act: 0.1472. Min Act: -0.0001

Data Index: 695581 (C4 (Web Text))

Max Activating Token Index: 172

Text #12

Max Range: 0.1594. Min Range: -0.1594

Max Act: 0.1380. Min Act: -0.0001

Data Index: 1209067 (C4 (Web Text))

Max Activating Token Index: 643

Text #13

Max Range: 0.1594. Min Range: -0.1594

Max Act: 0.1279. Min Act: -0.0001

Data Index: 705567 (C4 (Web Text))

Max Activating Token Index: 749

Text #14

Max Range: 0.1594. Min Range: -0.1594

Max Act: 0.1192. Min Act: -0.0001

Data Index: 1359347 (C4 (Web Text))

Max Activating Token Index: 784

Text #15

Max Range: 0.1594. Min Range: -0.1594

Max Act: 0.1454. Min Act: -0.0001

Data Index: 181656 (C4 (Web Text))

Max Activating Token Index: 50

Text #16

Max Range: 0.1594. Min Range: -0.1594

Max Act: 0.1349. Min Act: -0.0001

Data Index: 697526 (C4 (Web Text))

Max Activating Token Index: 1010

Text #17

Max Range: 0.1594. Min Range: -0.1594

Max Act: 0.1234. Min Act: -0.0001

Data Index: 680573 (C4 (Web Text))

Max Activating Token Index: 584

Text #18

Max Range: 0.1594. Min Range: -0.1594

Max Act: 0.1240. Min Act: -0.0001

Data Index: 971949 (C4 (Web Text))

Max Activating Token Index: 788

Text #19

Max Range: 0.1594. Min Range: -0.1594

Max Act: 0.1327. Min Act: -0.0001

Data Index: 334023 (C4 (Web Text))

Max Activating Token Index: 589