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

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

Neuron 846 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0649. Min Range: -1.0649

Max Act: 1.0649. Min Act: -0.0001

Data Index: 1583665 (Python Code)

Max Activating Token Index: 425

Text #1

Max Range: 1.0649. Min Range: -1.0649

Max Act: 1.0362. Min Act: -0.0001

Data Index: 601974 (C4 (Web Text))

Max Activating Token Index: 417

Text #2

Max Range: 1.0649. Min Range: -1.0649

Max Act: 1.0019. Min Act: -0.0001

Data Index: 637404 (C4 (Web Text))

Max Activating Token Index: 606

Text #3

Max Range: 1.0649. Min Range: -1.0649

Max Act: 0.9366. Min Act: -0.0001

Data Index: 1365470 (Python Code)

Max Activating Token Index: 189

Text #4

Max Range: 1.0649. Min Range: -1.0649

Max Act: 0.9486. Min Act: -0.0001

Data Index: 233742 (C4 (Web Text))

Max Activating Token Index: 593

Text #5

Max Range: 1.0649. Min Range: -1.0649

Max Act: 0.8156. Min Act: -0.0001

Data Index: 102139 (C4 (Web Text))

Max Activating Token Index: 538

Text #6

Max Range: 1.0649. Min Range: -1.0649

Max Act: 0.8079. Min Act: -0.0001

Data Index: 452087 (C4 (Web Text))

Max Activating Token Index: 1008

Text #7

Max Range: 1.0649. Min Range: -1.0649

Max Act: 0.7961. Min Act: -0.0001

Data Index: 278468 (C4 (Web Text))

Max Activating Token Index: 228

Text #8

Max Range: 1.0649. Min Range: -1.0649

Max Act: 0.8298. Min Act: -0.0001

Data Index: 309541 (C4 (Web Text))

Max Activating Token Index: 286

Text #9

Max Range: 1.0649. Min Range: -1.0649

Max Act: 0.7790. Min Act: -0.0001

Data Index: 1577695 (Python Code)

Max Activating Token Index: 470

Text #10

Max Range: 1.0649. Min Range: -1.0649

Max Act: 0.7627. Min Act: -0.0001

Data Index: 611236 (C4 (Web Text))

Max Activating Token Index: 720

Text #11

Max Range: 1.0649. Min Range: -1.0649

Max Act: 0.7771. Min Act: -0.0001

Data Index: 343058 (C4 (Web Text))

Max Activating Token Index: 282

Text #12

Max Range: 1.0649. Min Range: -1.0649

Max Act: 0.7768. Min Act: -0.0001

Data Index: 379812 (C4 (Web Text))

Max Activating Token Index: 90

Text #13

Max Range: 1.0649. Min Range: -1.0649

Max Act: 0.7452. Min Act: -0.0001

Data Index: 802362 (C4 (Web Text))

Max Activating Token Index: 595

Text #14

Max Range: 1.0649. Min Range: -1.0649

Max Act: 0.7658. Min Act: -0.0001

Data Index: 77876 (C4 (Web Text))

Max Activating Token Index: 639

Text #15

Max Range: 1.0649. Min Range: -1.0649

Max Act: 0.7310. Min Act: -0.0001

Data Index: 544773 (C4 (Web Text))

Max Activating Token Index: 511

Text #16

Max Range: 1.0649. Min Range: -1.0649

Max Act: 0.7260. Min Act: -0.0001

Data Index: 311727 (C4 (Web Text))

Max Activating Token Index: 358

Text #17

Max Range: 1.0649. Min Range: -1.0649

Max Act: 0.7223. Min Act: -0.0001

Data Index: 1132340 (C4 (Web Text))

Max Activating Token Index: 597

Text #18

Max Range: 1.0649. Min Range: -1.0649

Max Act: 0.7215. Min Act: -0.0001

Data Index: 508286 (C4 (Web Text))

Max Activating Token Index: 707

Text #19

Max Range: 1.0649. Min Range: -1.0649

Max Act: 0.6717. Min Act: -0.0001

Data Index: 1249240 (C4 (Web Text))

Max Activating Token Index: 181