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

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

Neuron 1104 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: 1.8883. Min Range: -1.8883

Max Act: 1.8883. Min Act: -0.0000

Data Index: 441830 (C4 (Web Text))

Max Activating Token Index: 625

Text #1

Max Range: 1.8883. Min Range: -1.8883

Max Act: 1.6928. Min Act: -0.0000

Data Index: 1297272 (C4 (Web Text))

Max Activating Token Index: 973

Text #2

Max Range: 1.8883. Min Range: -1.8883

Max Act: 1.7888. Min Act: -0.0000

Data Index: 269945 (C4 (Web Text))

Max Activating Token Index: 928

Text #3

Max Range: 1.8883. Min Range: -1.8883

Max Act: 1.7922. Min Act: -0.0000

Data Index: 781935 (C4 (Web Text))

Max Activating Token Index: 551

Text #4

Max Range: 1.8883. Min Range: -1.8883

Max Act: 1.5864. Min Act: -0.0000

Data Index: 474347 (C4 (Web Text))

Max Activating Token Index: 746

Text #5

Max Range: 1.8883. Min Range: -1.8883

Max Act: 1.6536. Min Act: -0.0000

Data Index: 461525 (C4 (Web Text))

Max Activating Token Index: 1021

Text #6

Max Range: 1.8883. Min Range: -1.8883

Max Act: 1.6503. Min Act: -0.0000

Data Index: 347693 (C4 (Web Text))

Max Activating Token Index: 785

Text #7

Max Range: 1.8883. Min Range: -1.8883

Max Act: 1.5512. Min Act: -0.0000

Data Index: 388920 (C4 (Web Text))

Max Activating Token Index: 482

Text #8

Max Range: 1.8883. Min Range: -1.8883

Max Act: 1.5269. Min Act: -0.0000

Data Index: 475619 (C4 (Web Text))

Max Activating Token Index: 450

Text #9

Max Range: 1.8883. Min Range: -1.8883

Max Act: 1.6274. Min Act: -0.0000

Data Index: 289329 (C4 (Web Text))

Max Activating Token Index: 65

Text #10

Max Range: 1.8883. Min Range: -1.8883

Max Act: 1.4575. Min Act: -0.0000

Data Index: 185244 (C4 (Web Text))

Max Activating Token Index: 718

Text #11

Max Range: 1.8883. Min Range: -1.8883

Max Act: 1.6629. Min Act: -0.0000

Data Index: 1309324 (C4 (Web Text))

Max Activating Token Index: 1002

Text #12

Max Range: 1.8883. Min Range: -1.8883

Max Act: 1.5414. Min Act: -0.0000

Data Index: 347589 (C4 (Web Text))

Max Activating Token Index: 919

Text #13

Max Range: 1.8883. Min Range: -1.8883

Max Act: 1.4714. Min Act: -0.0000

Data Index: 364407 (C4 (Web Text))

Max Activating Token Index: 884

Text #14

Max Range: 1.8883. Min Range: -1.8883

Max Act: 1.5168. Min Act: -0.0000

Data Index: 2421 (C4 (Web Text))

Max Activating Token Index: 228

Text #15

Max Range: 1.8883. Min Range: -1.8883

Max Act: 1.5237. Min Act: -0.0000

Data Index: 1046143 (C4 (Web Text))

Max Activating Token Index: 524

Text #16

Max Range: 1.8883. Min Range: -1.8883

Max Act: 1.6145. Min Act: -0.0000

Data Index: 150143 (C4 (Web Text))

Max Activating Token Index: 363

Text #17

Max Range: 1.8883. Min Range: -1.8883

Max Act: 1.4371. Min Act: -0.0000

Data Index: 441312 (C4 (Web Text))

Max Activating Token Index: 593

Text #18

Max Range: 1.8883. Min Range: -1.8883

Max Act: 1.4254. Min Act: -0.0000

Data Index: 532354 (C4 (Web Text))

Max Activating Token Index: 617

Text #19

Max Range: 1.8883. Min Range: -1.8883

Max Act: 1.3953. Min Act: -0.0000

Data Index: 991691 (C4 (Web Text))

Max Activating Token Index: 1008