Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 5902 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.4609. Min Range: -0.4609

Max Act: 0.4609. Min Act: -0.0000

Data Index: 226023 (C4 (Web Text))

Max Activating Token Index: 315

Text #1

Max Range: 0.4609. Min Range: -0.4609

Max Act: 0.4524. Min Act: -0.0000

Data Index: 862715 (C4 (Web Text))

Max Activating Token Index: 394

Text #2

Max Range: 0.4609. Min Range: -0.4609

Max Act: 0.4079. Min Act: -0.0000

Data Index: 1108074 (C4 (Web Text))

Max Activating Token Index: 336

Text #3

Max Range: 0.4609. Min Range: -0.4609

Max Act: 0.4253. Min Act: -0.0000

Data Index: 603915 (C4 (Web Text))

Max Activating Token Index: 383

Text #4

Max Range: 0.4609. Min Range: -0.4609

Max Act: 0.4364. Min Act: -0.0000

Data Index: 702191 (C4 (Web Text))

Max Activating Token Index: 745

Text #5

Max Range: 0.4609. Min Range: -0.4609

Max Act: 0.4531. Min Act: -0.0000

Data Index: 110229 (C4 (Web Text))

Max Activating Token Index: 221

Text #6

Max Range: 0.4609. Min Range: -0.4609

Max Act: 0.3777. Min Act: -0.0000

Data Index: 714120 (C4 (Web Text))

Max Activating Token Index: 407

Text #7

Max Range: 0.4609. Min Range: -0.4609

Max Act: 0.3767. Min Act: -0.0000

Data Index: 879182 (C4 (Web Text))

Max Activating Token Index: 869

Text #8

Max Range: 0.4609. Min Range: -0.4609

Max Act: 0.3855. Min Act: -0.0000

Data Index: 974528 (C4 (Web Text))

Max Activating Token Index: 138

Text #9

Max Range: 0.4609. Min Range: -0.4609

Max Act: 0.3806. Min Act: -0.0000

Data Index: 1127667 (C4 (Web Text))

Max Activating Token Index: 847

Text #10

Max Range: 0.4609. Min Range: -0.4609

Max Act: 0.3839. Min Act: -0.0000

Data Index: 1188642 (C4 (Web Text))

Max Activating Token Index: 760

Text #11

Max Range: 0.4609. Min Range: -0.4609

Max Act: 0.3795. Min Act: -0.0000

Data Index: 1479360 (Python Code)

Max Activating Token Index: 592

Text #12

Max Range: 0.4609. Min Range: -0.4609

Max Act: 0.3439. Min Act: -0.0000

Data Index: 228891 (C4 (Web Text))

Max Activating Token Index: 98

Text #13

Max Range: 0.4609. Min Range: -0.4609

Max Act: 0.3674. Min Act: -0.0000

Data Index: 1106116 (C4 (Web Text))

Max Activating Token Index: 294

Text #14

Max Range: 0.4609. Min Range: -0.4609

Max Act: 0.3492. Min Act: -0.0000

Data Index: 611736 (C4 (Web Text))

Max Activating Token Index: 382

Text #15

Max Range: 0.4609. Min Range: -0.4609

Max Act: 0.3457. Min Act: -0.0000

Data Index: 166839 (C4 (Web Text))

Max Activating Token Index: 408

Text #16

Max Range: 0.4609. Min Range: -0.4609

Max Act: 0.3323. Min Act: -0.0000

Data Index: 350956 (C4 (Web Text))

Max Activating Token Index: 221

Text #17

Max Range: 0.4609. Min Range: -0.4609

Max Act: 0.3213. Min Act: -0.0000

Data Index: 1185377 (C4 (Web Text))

Max Activating Token Index: 687

Text #18

Max Range: 0.4609. Min Range: -0.4609

Max Act: 0.3215. Min Act: -0.0000

Data Index: 238867 (C4 (Web Text))

Max Activating Token Index: 859

Text #19

Max Range: 0.4609. Min Range: -0.4609

Max Act: 0.3676. Min Act: -0.0000

Data Index: 965728 (C4 (Web Text))

Max Activating Token Index: 364