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

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

Neuron 3848 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: 0.1956. Min Range: -0.1956

Max Act: 0.1956. Min Act: -0.0001

Data Index: 536692 (C4 (Web Text))

Max Activating Token Index: 842

Text #1

Max Range: 0.1956. Min Range: -0.1956

Max Act: 0.1752. Min Act: -0.0001

Data Index: 866036 (C4 (Web Text))

Max Activating Token Index: 794

Text #2

Max Range: 0.1956. Min Range: -0.1956

Max Act: 0.1633. Min Act: -0.0001

Data Index: 968786 (C4 (Web Text))

Max Activating Token Index: 527

Text #3

Max Range: 0.1956. Min Range: -0.1956

Max Act: 0.1693. Min Act: -0.0001

Data Index: 474938 (C4 (Web Text))

Max Activating Token Index: 58

Text #4

Max Range: 0.1956. Min Range: -0.1956

Max Act: 0.1611. Min Act: -0.0001

Data Index: 887973 (C4 (Web Text))

Max Activating Token Index: 622

Text #5

Max Range: 0.1956. Min Range: -0.1956

Max Act: 0.1672. Min Act: -0.0001

Data Index: 140176 (C4 (Web Text))

Max Activating Token Index: 301

Text #6

Max Range: 0.1956. Min Range: -0.1956

Max Act: 0.1657. Min Act: -0.0001

Data Index: 244990 (C4 (Web Text))

Max Activating Token Index: 607

Text #7

Max Range: 0.1956. Min Range: -0.1956

Max Act: 0.1622. Min Act: -0.0001

Data Index: 309015 (C4 (Web Text))

Max Activating Token Index: 635

Text #8

Max Range: 0.1956. Min Range: -0.1956

Max Act: 0.1623. Min Act: -0.0001

Data Index: 1321235 (C4 (Web Text))

Max Activating Token Index: 291

Text #9

Max Range: 0.1956. Min Range: -0.1956

Max Act: 0.1584. Min Act: -0.0001

Data Index: 1254732 (C4 (Web Text))

Max Activating Token Index: 287

Text #10

Max Range: 0.1956. Min Range: -0.1956

Max Act: 0.1474. Min Act: -0.0001

Data Index: 507257 (C4 (Web Text))

Max Activating Token Index: 443

Text #11

Max Range: 0.1956. Min Range: -0.1956

Max Act: 0.1512. Min Act: -0.0001

Data Index: 972636 (C4 (Web Text))

Max Activating Token Index: 200

Text #12

Max Range: 0.1956. Min Range: -0.1956

Max Act: 0.1499. Min Act: -0.0001

Data Index: 424752 (C4 (Web Text))

Max Activating Token Index: 345

Text #13

Max Range: 0.1956. Min Range: -0.1956

Max Act: 0.1533. Min Act: -0.0001

Data Index: 5685 (C4 (Web Text))

Max Activating Token Index: 192

Text #14

Max Range: 0.1956. Min Range: -0.1956

Max Act: 0.1385. Min Act: -0.0001

Data Index: 699712 (C4 (Web Text))

Max Activating Token Index: 137

Text #15

Max Range: 0.1956. Min Range: -0.1956

Max Act: 0.1292. Min Act: -0.0001

Data Index: 640461 (C4 (Web Text))

Max Activating Token Index: 839

Text #16

Max Range: 0.1956. Min Range: -0.1956

Max Act: 0.1287. Min Act: -0.0001

Data Index: 696144 (C4 (Web Text))

Max Activating Token Index: 259

Text #17

Max Range: 0.1956. Min Range: -0.1956

Max Act: 0.1277. Min Act: -0.0001

Data Index: 984349 (C4 (Web Text))

Max Activating Token Index: 601

Text #18

Max Range: 0.1956. Min Range: -0.1956

Max Act: 0.1278. Min Act: -0.0001

Data Index: 1198215 (C4 (Web Text))

Max Activating Token Index: 117

Text #19

Max Range: 0.1956. Min Range: -0.1956

Max Act: 0.1319. Min Act: -0.0001

Data Index: 581915 (C4 (Web Text))

Max Activating Token Index: 142