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

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

Neuron 40 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: 0.8286. Min Range: -0.8286

Max Act: 0.8286. Min Act: -0.0001

Data Index: 1025626 (C4 (Web Text))

Max Activating Token Index: 814

Text #1

Max Range: 0.8286. Min Range: -0.8286

Max Act: 0.7256. Min Act: -0.0001

Data Index: 256362 (C4 (Web Text))

Max Activating Token Index: 44

Text #2

Max Range: 0.8286. Min Range: -0.8286

Max Act: 0.7292. Min Act: -0.0001

Data Index: 385458 (C4 (Web Text))

Max Activating Token Index: 491

Text #3

Max Range: 0.8286. Min Range: -0.8286

Max Act: 0.7485. Min Act: -0.0001

Data Index: 367482 (C4 (Web Text))

Max Activating Token Index: 442

Text #4

Max Range: 0.8286. Min Range: -0.8286

Max Act: 0.7102. Min Act: -0.0001

Data Index: 683683 (C4 (Web Text))

Max Activating Token Index: 1016

Text #5

Max Range: 0.8286. Min Range: -0.8286

Max Act: 0.6800. Min Act: -0.0001

Data Index: 938556 (C4 (Web Text))

Max Activating Token Index: 619

Text #6

Max Range: 0.8286. Min Range: -0.8286

Max Act: 0.6732. Min Act: -0.0001

Data Index: 728334 (C4 (Web Text))

Max Activating Token Index: 479

Text #7

Max Range: 0.8286. Min Range: -0.8286

Max Act: 0.6657. Min Act: -0.0001

Data Index: 993777 (C4 (Web Text))

Max Activating Token Index: 473

Text #8

Max Range: 0.8286. Min Range: -0.8286

Max Act: 0.6627. Min Act: -0.0001

Data Index: 459913 (C4 (Web Text))

Max Activating Token Index: 407

Text #9

Max Range: 0.8286. Min Range: -0.8286

Max Act: 0.6407. Min Act: -0.0001

Data Index: 982000 (C4 (Web Text))

Max Activating Token Index: 77

Text #10

Max Range: 0.8286. Min Range: -0.8286

Max Act: 0.6747. Min Act: -0.0001

Data Index: 1130683 (C4 (Web Text))

Max Activating Token Index: 172

Text #11

Max Range: 0.8286. Min Range: -0.8286

Max Act: 0.6816. Min Act: -0.0001

Data Index: 794472 (C4 (Web Text))

Max Activating Token Index: 547

Text #12

Max Range: 0.8286. Min Range: -0.8286

Max Act: 0.6739. Min Act: -0.0001

Data Index: 681343 (C4 (Web Text))

Max Activating Token Index: 196

Text #13

Max Range: 0.8286. Min Range: -0.8286

Max Act: 0.6318. Min Act: -0.0001

Data Index: 368160 (C4 (Web Text))

Max Activating Token Index: 362

Text #14

Max Range: 0.8286. Min Range: -0.8286

Max Act: 0.6463. Min Act: -0.0001

Data Index: 600023 (C4 (Web Text))

Max Activating Token Index: 430

Text #15

Max Range: 0.8286. Min Range: -0.8286

Max Act: 0.6663. Min Act: -0.0001

Data Index: 370063 (C4 (Web Text))

Max Activating Token Index: 993

Text #16

Max Range: 0.8286. Min Range: -0.8286

Max Act: 0.6202. Min Act: -0.0001

Data Index: 659339 (C4 (Web Text))

Max Activating Token Index: 615

Text #17

Max Range: 0.8286. Min Range: -0.8286

Max Act: 0.6401. Min Act: -0.0001

Data Index: 341377 (C4 (Web Text))

Max Activating Token Index: 665

Text #18

Max Range: 0.8286. Min Range: -0.8286

Max Act: 0.6229. Min Act: -0.0001

Data Index: 1247546 (C4 (Web Text))

Max Activating Token Index: 310

Text #19

Max Range: 0.8286. Min Range: -0.8286

Max Act: 0.6101. Min Act: -0.0001

Data Index: 1032550 (C4 (Web Text))

Max Activating Token Index: 906