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

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

Neuron 4513 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.4327. Min Range: -5.4327

Max Act: 5.1417. Min Act: -0.0001

Data Index: 826453 (C4 (Web Text))

Max Activating Token Index: 569

Text #1

Max Range: 5.4327. Min Range: -5.4327

Max Act: 5.1493. Min Act: -0.0001

Data Index: 841465 (C4 (Web Text))

Max Activating Token Index: 434

Text #2

Max Range: 5.4327. Min Range: -5.4327

Max Act: 5.4327. Min Act: -0.0001

Data Index: 654391 (C4 (Web Text))

Max Activating Token Index: 97

Text #3

Max Range: 5.4327. Min Range: -5.4327

Max Act: 4.3450. Min Act: -0.0001

Data Index: 1356736 (C4 (Web Text))

Max Activating Token Index: 720

Text #4

Max Range: 5.4327. Min Range: -5.4327

Max Act: 5.1354. Min Act: -0.0001

Data Index: 193639 (C4 (Web Text))

Max Activating Token Index: 874

Text #5

Max Range: 5.4327. Min Range: -5.4327

Max Act: 4.5311. Min Act: -0.0001

Data Index: 1161212 (C4 (Web Text))

Max Activating Token Index: 404

Text #6

Max Range: 5.4327. Min Range: -5.4327

Max Act: 4.7978. Min Act: -0.0001

Data Index: 833867 (C4 (Web Text))

Max Activating Token Index: 454

Text #7

Max Range: 5.4327. Min Range: -5.4327

Max Act: 4.5421. Min Act: -0.0001

Data Index: 477322 (C4 (Web Text))

Max Activating Token Index: 194

Text #8

Max Range: 5.4327. Min Range: -5.4327

Max Act: 4.2763. Min Act: -0.0001

Data Index: 815973 (C4 (Web Text))

Max Activating Token Index: 663

Text #9

Max Range: 5.4327. Min Range: -5.4327

Max Act: 4.4026. Min Act: -0.0001

Data Index: 541083 (C4 (Web Text))

Max Activating Token Index: 365

Text #10

Max Range: 5.4327. Min Range: -5.4327

Max Act: 4.1052. Min Act: -0.0001

Data Index: 814845 (C4 (Web Text))

Max Activating Token Index: 866

Text #11

Max Range: 5.4327. Min Range: -5.4327

Max Act: 4.2329. Min Act: -0.0001

Data Index: 1121794 (C4 (Web Text))

Max Activating Token Index: 577

Text #12

Max Range: 5.4327. Min Range: -5.4327

Max Act: 4.6476. Min Act: -0.0001

Data Index: 936798 (C4 (Web Text))

Max Activating Token Index: 772

Text #13

Max Range: 5.4327. Min Range: -5.4327

Max Act: 4.5714. Min Act: -0.0001

Data Index: 151780 (C4 (Web Text))

Max Activating Token Index: 637

Text #14

Max Range: 5.4327. Min Range: -5.4327

Max Act: 4.1726. Min Act: -0.0001

Data Index: 417587 (C4 (Web Text))

Max Activating Token Index: 223

Text #15

Max Range: 5.4327. Min Range: -5.4327

Max Act: 4.0275. Min Act: -0.0001

Data Index: 1092083 (C4 (Web Text))

Max Activating Token Index: 558

Text #16

Max Range: 5.4327. Min Range: -5.4327

Max Act: 3.9946. Min Act: -0.0001

Data Index: 81107 (C4 (Web Text))

Max Activating Token Index: 468

Text #17

Max Range: 5.4327. Min Range: -5.4327

Max Act: 3.8598. Min Act: -0.0001

Data Index: 345210 (C4 (Web Text))

Max Activating Token Index: 260

Text #18

Max Range: 5.4327. Min Range: -5.4327

Max Act: 3.8646. Min Act: -0.0001

Data Index: 814019 (C4 (Web Text))

Max Activating Token Index: 78

Text #19

Max Range: 5.4327. Min Range: -5.4327

Max Act: 4.1611. Min Act: -0.0001

Data Index: 535256 (C4 (Web Text))

Max Activating Token Index: 789