Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 304 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.4359. Min Range: -0.4359

Max Act: 0.4359. Min Act: -0.0001

Data Index: 225045 (C4 (Web Text))

Max Activating Token Index: 216

Text #1

Max Range: 0.4359. Min Range: -0.4359

Max Act: 0.4313. Min Act: -0.0001

Data Index: 1642732 (Python Code)

Max Activating Token Index: 245

Text #2

Max Range: 0.4359. Min Range: -0.4359

Max Act: 0.3728. Min Act: -0.0001

Data Index: 912856 (C4 (Web Text))

Max Activating Token Index: 662

Text #3

Max Range: 0.4359. Min Range: -0.4359

Max Act: 0.3811. Min Act: -0.0001

Data Index: 556289 (C4 (Web Text))

Max Activating Token Index: 327

Text #4

Max Range: 0.4359. Min Range: -0.4359

Max Act: 0.3603. Min Act: -0.0001

Data Index: 1647278 (Python Code)

Max Activating Token Index: 909

Text #5

Max Range: 0.4359. Min Range: -0.4359

Max Act: 0.3494. Min Act: -0.0001

Data Index: 390923 (C4 (Web Text))

Max Activating Token Index: 635

Text #6

Max Range: 0.4359. Min Range: -0.4359

Max Act: 0.3532. Min Act: -0.0001

Data Index: 792065 (C4 (Web Text))

Max Activating Token Index: 919

Text #7

Max Range: 0.4359. Min Range: -0.4359

Max Act: 0.3542. Min Act: -0.0001

Data Index: 940788 (C4 (Web Text))

Max Activating Token Index: 288

Text #8

Max Range: 0.4359. Min Range: -0.4359

Max Act: 0.3776. Min Act: -0.0001

Data Index: 796062 (C4 (Web Text))

Max Activating Token Index: 418

Text #9

Max Range: 0.4359. Min Range: -0.4359

Max Act: 0.3358. Min Act: -0.0001

Data Index: 142081 (C4 (Web Text))

Max Activating Token Index: 96

Text #10

Max Range: 0.4359. Min Range: -0.4359

Max Act: 0.3475. Min Act: -0.0001

Data Index: 718505 (C4 (Web Text))

Max Activating Token Index: 82

Text #11

Max Range: 0.4359. Min Range: -0.4359

Max Act: 0.3466. Min Act: -0.0001

Data Index: 771520 (C4 (Web Text))

Max Activating Token Index: 604

Text #12

Max Range: 0.4359. Min Range: -0.4359

Max Act: 0.3189. Min Act: -0.0001

Data Index: 1037106 (C4 (Web Text))

Max Activating Token Index: 905

Text #13

Max Range: 0.4359. Min Range: -0.4359

Max Act: 0.3663. Min Act: -0.0001

Data Index: 1536538 (Python Code)

Max Activating Token Index: 946

Text #14

Max Range: 0.4359. Min Range: -0.4359

Max Act: 0.3529. Min Act: -0.0001

Data Index: 29691 (C4 (Web Text))

Max Activating Token Index: 825

Text #15

Max Range: 0.4359. Min Range: -0.4359

Max Act: 0.3297. Min Act: -0.0001

Data Index: 1125277 (C4 (Web Text))

Max Activating Token Index: 225

Text #16

Max Range: 0.4359. Min Range: -0.4359

Max Act: 0.3314. Min Act: -0.0001

Data Index: 1275942 (C4 (Web Text))

Max Activating Token Index: 868

Text #17

Max Range: 0.4359. Min Range: -0.4359

Max Act: 0.3253. Min Act: -0.0001

Data Index: 742568 (C4 (Web Text))

Max Activating Token Index: 766

Text #18

Max Range: 0.4359. Min Range: -0.4359

Max Act: 0.3230. Min Act: -0.0001

Data Index: 1369475 (Python Code)

Max Activating Token Index: 1004

Text #19

Max Range: 0.4359. Min Range: -0.4359

Max Act: 0.3043. Min Act: -0.0001

Data Index: 392544 (C4 (Web Text))

Max Activating Token Index: 535