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

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

Neuron 556 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0468. Min Range: -0.0468

Max Act: 0.0460. Min Act: -0.0000

Data Index: 50141 (C4 (Web Text))

Max Activating Token Index: 762

Text #1

Max Range: 0.0468. Min Range: -0.0468

Max Act: 0.0468. Min Act: -0.0000

Data Index: 1282937 (C4 (Web Text))

Max Activating Token Index: 996

Text #2

Max Range: 0.0468. Min Range: -0.0468

Max Act: 0.0439. Min Act: -0.0000

Data Index: 642636 (C4 (Web Text))

Max Activating Token Index: 465

Text #3

Max Range: 0.0468. Min Range: -0.0468

Max Act: 0.0354. Min Act: -0.0000

Data Index: 1620680 (Python Code)

Max Activating Token Index: 1006

Text #4

Max Range: 0.0468. Min Range: -0.0468

Max Act: 0.0358. Min Act: -0.0000

Data Index: 676135 (C4 (Web Text))

Max Activating Token Index: 387

Text #5

Max Range: 0.0468. Min Range: -0.0468

Max Act: 0.0358. Min Act: -0.0000

Data Index: 1149150 (C4 (Web Text))

Max Activating Token Index: 828

Text #6

Max Range: 0.0468. Min Range: -0.0468

Max Act: 0.0355. Min Act: -0.0000

Data Index: 1080666 (C4 (Web Text))

Max Activating Token Index: 149

Text #7

Max Range: 0.0468. Min Range: -0.0468

Max Act: 0.0350. Min Act: -0.0000

Data Index: 1149969 (C4 (Web Text))

Max Activating Token Index: 672

Text #8

Max Range: 0.0468. Min Range: -0.0468

Max Act: 0.0322. Min Act: -0.0001

Data Index: 1146983 (C4 (Web Text))

Max Activating Token Index: 707

Text #9

Max Range: 0.0468. Min Range: -0.0468

Max Act: 0.0339. Min Act: -0.0000

Data Index: 158964 (C4 (Web Text))

Max Activating Token Index: 690

Text #10

Max Range: 0.0468. Min Range: -0.0468

Max Act: 0.0334. Min Act: -0.0000

Data Index: 1591700 (Python Code)

Max Activating Token Index: 846

Text #11

Max Range: 0.0468. Min Range: -0.0468

Max Act: 0.0338. Min Act: -0.0000

Data Index: 1088783 (C4 (Web Text))

Max Activating Token Index: 476

Text #12

Max Range: 0.0468. Min Range: -0.0468

Max Act: 0.0355. Min Act: -0.0000

Data Index: 90613 (C4 (Web Text))

Max Activating Token Index: 314

Text #13

Max Range: 0.0468. Min Range: -0.0468

Max Act: 0.0342. Min Act: -0.0000

Data Index: 678616 (C4 (Web Text))

Max Activating Token Index: 617

Text #14

Max Range: 0.0468. Min Range: -0.0468

Max Act: 0.0284. Min Act: -0.0000

Data Index: 1164467 (C4 (Web Text))

Max Activating Token Index: 676

Text #15

Max Range: 0.0468. Min Range: -0.0468

Max Act: 0.0346. Min Act: -0.0000

Data Index: 594318 (C4 (Web Text))

Max Activating Token Index: 394

Text #16

Max Range: 0.0468. Min Range: -0.0468

Max Act: 0.0323. Min Act: -0.0000

Data Index: 691118 (C4 (Web Text))

Max Activating Token Index: 496

Text #17

Max Range: 0.0468. Min Range: -0.0468

Max Act: 0.0318. Min Act: -0.0000

Data Index: 716551 (C4 (Web Text))

Max Activating Token Index: 845

Text #18

Max Range: 0.0468. Min Range: -0.0468

Max Act: 0.0327. Min Act: -0.0000

Data Index: 1394681 (Python Code)

Max Activating Token Index: 950

Text #19

Max Range: 0.0468. Min Range: -0.0468

Max Act: 0.0335. Min Act: -0.0000

Data Index: 623190 (C4 (Web Text))

Max Activating Token Index: 215