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

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

Neuron 562 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4855. Min Range: -0.4855

Max Act: 0.4855. Min Act: -0.0001

Data Index: 1534397 (Python Code)

Max Activating Token Index: 739

Text #1

Max Range: 0.4855. Min Range: -0.4855

Max Act: 0.4829. Min Act: -0.0000

Data Index: 806973 (C4 (Web Text))

Max Activating Token Index: 950

Text #2

Max Range: 0.4855. Min Range: -0.4855

Max Act: 0.4416. Min Act: -0.0001

Data Index: 1529309 (Python Code)

Max Activating Token Index: 859

Text #3

Max Range: 0.4855. Min Range: -0.4855

Max Act: 0.4376. Min Act: -0.0000

Data Index: 1004241 (C4 (Web Text))

Max Activating Token Index: 1014

Text #4

Max Range: 0.4855. Min Range: -0.4855

Max Act: 0.4046. Min Act: -0.0001

Data Index: 1362153 (Python Code)

Max Activating Token Index: 771

Text #5

Max Range: 0.4855. Min Range: -0.4855

Max Act: 0.3995. Min Act: -0.0000

Data Index: 164542 (C4 (Web Text))

Max Activating Token Index: 366

Text #6

Max Range: 0.4855. Min Range: -0.4855

Max Act: 0.3821. Min Act: -0.0000

Data Index: 881299 (C4 (Web Text))

Max Activating Token Index: 939

Text #7

Max Range: 0.4855. Min Range: -0.4855

Max Act: 0.3737. Min Act: -0.0001

Data Index: 358572 (C4 (Web Text))

Max Activating Token Index: 523

Text #8

Max Range: 0.4855. Min Range: -0.4855

Max Act: 0.3427. Min Act: -0.0001

Data Index: 681464 (C4 (Web Text))

Max Activating Token Index: 809

Text #9

Max Range: 0.4855. Min Range: -0.4855

Max Act: 0.3323. Min Act: -0.0000

Data Index: 471091 (C4 (Web Text))

Max Activating Token Index: 377

Text #10

Max Range: 0.4855. Min Range: -0.4855

Max Act: 0.3292. Min Act: -0.0001

Data Index: 874376 (C4 (Web Text))

Max Activating Token Index: 558

Text #11

Max Range: 0.4855. Min Range: -0.4855

Max Act: 0.3468. Min Act: -0.0001

Data Index: 1266580 (C4 (Web Text))

Max Activating Token Index: 875

Text #12

Max Range: 0.4855. Min Range: -0.4855

Max Act: 0.3251. Min Act: -0.0001

Data Index: 87193 (C4 (Web Text))

Max Activating Token Index: 47

Text #13

Max Range: 0.4855. Min Range: -0.4855

Max Act: 0.3331. Min Act: -0.0001

Data Index: 790431 (C4 (Web Text))

Max Activating Token Index: 296

Text #14

Max Range: 0.4855. Min Range: -0.4855

Max Act: 0.3170. Min Act: -0.0000

Data Index: 6024 (C4 (Web Text))

Max Activating Token Index: 403

Text #15

Max Range: 0.4855. Min Range: -0.4855

Max Act: 0.3398. Min Act: -0.0001

Data Index: 417210 (C4 (Web Text))

Max Activating Token Index: 461

Text #16

Max Range: 0.4855. Min Range: -0.4855

Max Act: 0.3158. Min Act: -0.0000

Data Index: 43328 (C4 (Web Text))

Max Activating Token Index: 710

Text #17

Max Range: 0.4855. Min Range: -0.4855

Max Act: 0.3224. Min Act: -0.0000

Data Index: 491839 (C4 (Web Text))

Max Activating Token Index: 477

Text #18

Max Range: 0.4855. Min Range: -0.4855

Max Act: 0.3312. Min Act: -0.0001

Data Index: 478518 (C4 (Web Text))

Max Activating Token Index: 703

Text #19

Max Range: 0.4855. Min Range: -0.4855

Max Act: 0.3293. Min Act: -0.0000

Data Index: 29610 (C4 (Web Text))

Max Activating Token Index: 273