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

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

Neuron 2797 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.6209. Min Range: -1.6209

Max Act: 1.6209. Min Act: -0.0000

Data Index: 131837 (C4 (Web Text))

Max Activating Token Index: 903

Text #1

Max Range: 1.6209. Min Range: -1.6209

Max Act: 1.5813. Min Act: -0.0000

Data Index: 943943 (C4 (Web Text))

Max Activating Token Index: 279

Text #2

Max Range: 1.6209. Min Range: -1.6209

Max Act: 1.4790. Min Act: -0.0000

Data Index: 142040 (C4 (Web Text))

Max Activating Token Index: 359

Text #3

Max Range: 1.6209. Min Range: -1.6209

Max Act: 1.4777. Min Act: -0.0000

Data Index: 739512 (C4 (Web Text))

Max Activating Token Index: 988

Text #4

Max Range: 1.6209. Min Range: -1.6209

Max Act: 1.4803. Min Act: -0.0000

Data Index: 248334 (C4 (Web Text))

Max Activating Token Index: 342

Text #5

Max Range: 1.6209. Min Range: -1.6209

Max Act: 1.5380. Min Act: -0.0000

Data Index: 27643 (C4 (Web Text))

Max Activating Token Index: 1006

Text #6

Max Range: 1.6209. Min Range: -1.6209

Max Act: 1.5177. Min Act: -0.0000

Data Index: 1007190 (C4 (Web Text))

Max Activating Token Index: 931

Text #7

Max Range: 1.6209. Min Range: -1.6209

Max Act: 1.4290. Min Act: -0.0000

Data Index: 518382 (C4 (Web Text))

Max Activating Token Index: 354

Text #8

Max Range: 1.6209. Min Range: -1.6209

Max Act: 1.5128. Min Act: -0.0000

Data Index: 203928 (C4 (Web Text))

Max Activating Token Index: 271

Text #9

Max Range: 1.6209. Min Range: -1.6209

Max Act: 1.4903. Min Act: -0.0000

Data Index: 543387 (C4 (Web Text))

Max Activating Token Index: 348

Text #10

Max Range: 1.6209. Min Range: -1.6209

Max Act: 1.4997. Min Act: -0.0000

Data Index: 973102 (C4 (Web Text))

Max Activating Token Index: 972

Text #11

Max Range: 1.6209. Min Range: -1.6209

Max Act: 1.4835. Min Act: -0.0000

Data Index: 58891 (C4 (Web Text))

Max Activating Token Index: 616

Text #12

Max Range: 1.6209. Min Range: -1.6209

Max Act: 1.4982. Min Act: -0.0000

Data Index: 173568 (C4 (Web Text))

Max Activating Token Index: 812

Text #13

Max Range: 1.6209. Min Range: -1.6209

Max Act: 1.3860. Min Act: -0.0000

Data Index: 311825 (C4 (Web Text))

Max Activating Token Index: 326

Text #14

Max Range: 1.6209. Min Range: -1.6209

Max Act: 1.4606. Min Act: -0.0000

Data Index: 33407 (C4 (Web Text))

Max Activating Token Index: 687

Text #15

Max Range: 1.6209. Min Range: -1.6209

Max Act: 1.4364. Min Act: -0.0000

Data Index: 771791 (C4 (Web Text))

Max Activating Token Index: 188

Text #16

Max Range: 1.6209. Min Range: -1.6209

Max Act: 1.3531. Min Act: -0.0000

Data Index: 980979 (C4 (Web Text))

Max Activating Token Index: 217

Text #17

Max Range: 1.6209. Min Range: -1.6209

Max Act: 1.3721. Min Act: -0.0000

Data Index: 583796 (C4 (Web Text))

Max Activating Token Index: 517

Text #18

Max Range: 1.6209. Min Range: -1.6209

Max Act: 1.3529. Min Act: -0.0000

Data Index: 125416 (C4 (Web Text))

Max Activating Token Index: 671

Text #19

Max Range: 1.6209. Min Range: -1.6209

Max Act: 1.4503. Min Act: -0.0000

Data Index: 645446 (C4 (Web Text))

Max Activating Token Index: 957