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

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

Neuron 1338 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0475. Min Range: -0.0475

Max Act: 0.0475. Min Act: -0.0001

Data Index: 156064 (C4 (Web Text))

Max Activating Token Index: 783

Text #1

Max Range: 0.0475. Min Range: -0.0475

Max Act: 0.0463. Min Act: -0.0001

Data Index: 1013722 (C4 (Web Text))

Max Activating Token Index: 727

Text #2

Max Range: 0.0475. Min Range: -0.0475

Max Act: 0.0457. Min Act: -0.0001

Data Index: 1345650 (C4 (Web Text))

Max Activating Token Index: 921

Text #3

Max Range: 0.0475. Min Range: -0.0475

Max Act: 0.0429. Min Act: -0.0001

Data Index: 526031 (C4 (Web Text))

Max Activating Token Index: 312

Text #4

Max Range: 0.0475. Min Range: -0.0475

Max Act: 0.0417. Min Act: -0.0001

Data Index: 957895 (C4 (Web Text))

Max Activating Token Index: 511

Text #5

Max Range: 0.0475. Min Range: -0.0475

Max Act: 0.0426. Min Act: -0.0001

Data Index: 260582 (C4 (Web Text))

Max Activating Token Index: 421

Text #6

Max Range: 0.0475. Min Range: -0.0475

Max Act: 0.0440. Min Act: -0.0001

Data Index: 1205204 (C4 (Web Text))

Max Activating Token Index: 992

Text #7

Max Range: 0.0475. Min Range: -0.0475

Max Act: 0.0410. Min Act: -0.0001

Data Index: 1269431 (C4 (Web Text))

Max Activating Token Index: 152

Text #8

Max Range: 0.0475. Min Range: -0.0475

Max Act: 0.0458. Min Act: -0.0001

Data Index: 1181347 (C4 (Web Text))

Max Activating Token Index: 985

Text #9

Max Range: 0.0475. Min Range: -0.0475

Max Act: 0.0437. Min Act: -0.0001

Data Index: 1246918 (C4 (Web Text))

Max Activating Token Index: 997

Text #10

Max Range: 0.0475. Min Range: -0.0475

Max Act: 0.0419. Min Act: -0.0001

Data Index: 305443 (C4 (Web Text))

Max Activating Token Index: 261

Text #11

Max Range: 0.0475. Min Range: -0.0475

Max Act: 0.0403. Min Act: -0.0001

Data Index: 817512 (C4 (Web Text))

Max Activating Token Index: 710

Text #12

Max Range: 0.0475. Min Range: -0.0475

Max Act: 0.0430. Min Act: -0.0001

Data Index: 304568 (C4 (Web Text))

Max Activating Token Index: 471

Text #13

Max Range: 0.0475. Min Range: -0.0475

Max Act: 0.0395. Min Act: -0.0001

Data Index: 357195 (C4 (Web Text))

Max Activating Token Index: 210

Text #14

Max Range: 0.0475. Min Range: -0.0475

Max Act: 0.0379. Min Act: -0.0001

Data Index: 834405 (C4 (Web Text))

Max Activating Token Index: 920

Text #15

Max Range: 0.0475. Min Range: -0.0475

Max Act: 0.0388. Min Act: -0.0001

Data Index: 298397 (C4 (Web Text))

Max Activating Token Index: 632

Text #16

Max Range: 0.0475. Min Range: -0.0475

Max Act: 0.0383. Min Act: -0.0001

Data Index: 1462741 (Python Code)

Max Activating Token Index: 927

Text #17

Max Range: 0.0475. Min Range: -0.0475

Max Act: 0.0412. Min Act: -0.0001

Data Index: 1219579 (C4 (Web Text))

Max Activating Token Index: 676

Text #18

Max Range: 0.0475. Min Range: -0.0475

Max Act: 0.0392. Min Act: -0.0001

Data Index: 1237034 (C4 (Web Text))

Max Activating Token Index: 441

Text #19

Max Range: 0.0475. Min Range: -0.0475

Max Act: 0.0393. Min Act: -0.0001

Data Index: 480941 (C4 (Web Text))

Max Activating Token Index: 789