Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 1239 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.0579. Min Range: -0.0579

Max Act: 0.0579. Min Act: -0.0002

Data Index: 381456 (C4 (Web Text))

Max Activating Token Index: 898

Text #1

Max Range: 0.0579. Min Range: -0.0579

Max Act: 0.0537. Min Act: -0.0001

Data Index: 384276 (C4 (Web Text))

Max Activating Token Index: 42

Text #2

Max Range: 0.0579. Min Range: -0.0579

Max Act: 0.0517. Min Act: -0.0002

Data Index: 1024658 (C4 (Web Text))

Max Activating Token Index: 499

Text #3

Max Range: 0.0579. Min Range: -0.0579

Max Act: 0.0504. Min Act: -0.0002

Data Index: 804358 (C4 (Web Text))

Max Activating Token Index: 166

Text #4

Max Range: 0.0579. Min Range: -0.0579

Max Act: 0.0497. Min Act: -0.0002

Data Index: 1303523 (C4 (Web Text))

Max Activating Token Index: 254

Text #5

Max Range: 0.0579. Min Range: -0.0579

Max Act: 0.0490. Min Act: -0.0002

Data Index: 1246304 (C4 (Web Text))

Max Activating Token Index: 400

Text #6

Max Range: 0.0579. Min Range: -0.0579

Max Act: 0.0496. Min Act: -0.0001

Data Index: 1046855 (C4 (Web Text))

Max Activating Token Index: 443

Text #7

Max Range: 0.0579. Min Range: -0.0579

Max Act: 0.0493. Min Act: -0.0002

Data Index: 280924 (C4 (Web Text))

Max Activating Token Index: 769

Text #8

Max Range: 0.0579. Min Range: -0.0579

Max Act: 0.0472. Min Act: -0.0002

Data Index: 1083329 (C4 (Web Text))

Max Activating Token Index: 466

Text #9

Max Range: 0.0579. Min Range: -0.0579

Max Act: 0.0471. Min Act: -0.0001

Data Index: 219077 (C4 (Web Text))

Max Activating Token Index: 873

Text #10

Max Range: 0.0579. Min Range: -0.0579

Max Act: 0.0473. Min Act: -0.0000

Data Index: 1035984 (C4 (Web Text))

Max Activating Token Index: 81

Text #11

Max Range: 0.0579. Min Range: -0.0579

Max Act: 0.0462. Min Act: -0.0002

Data Index: 709274 (C4 (Web Text))

Max Activating Token Index: 627

Text #12

Max Range: 0.0579. Min Range: -0.0579

Max Act: 0.0444. Min Act: -0.0001

Data Index: 1234333 (C4 (Web Text))

Max Activating Token Index: 489

Text #13

Max Range: 0.0579. Min Range: -0.0579

Max Act: 0.0462. Min Act: -0.0001

Data Index: 696594 (C4 (Web Text))

Max Activating Token Index: 207

Text #14

Max Range: 0.0579. Min Range: -0.0579

Max Act: 0.0460. Min Act: -0.0002

Data Index: 842897 (C4 (Web Text))

Max Activating Token Index: 933

Text #15

Max Range: 0.0579. Min Range: -0.0579

Max Act: 0.0456. Min Act: -0.0001

Data Index: 1176910 (C4 (Web Text))

Max Activating Token Index: 99

Text #16

Max Range: 0.0579. Min Range: -0.0579

Max Act: 0.0457. Min Act: -0.0001

Data Index: 1353553 (C4 (Web Text))

Max Activating Token Index: 904

Text #17

Max Range: 0.0579. Min Range: -0.0579

Max Act: 0.0449. Min Act: -0.0002

Data Index: 995665 (C4 (Web Text))

Max Activating Token Index: 178

Text #18

Max Range: 0.0579. Min Range: -0.0579

Max Act: 0.0438. Min Act: -0.0002

Data Index: 902425 (C4 (Web Text))

Max Activating Token Index: 302

Text #19

Max Range: 0.0579. Min Range: -0.0579

Max Act: 0.0445. Min Act: -0.0000

Data Index: 905079 (C4 (Web Text))

Max Activating Token Index: 201