Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 365 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 1.5727. Min Range: -1.5727

Max Act: 1.4728. Min Act: -0.0001

Data Index: 701253 (C4 (Web Text))

Max Activating Token Index: 288

Text #1

Max Range: 1.5727. Min Range: -1.5727

Max Act: 1.2068. Min Act: -0.0001

Data Index: 736393 (C4 (Web Text))

Max Activating Token Index: 585

Text #2

Max Range: 1.5727. Min Range: -1.5727

Max Act: 1.5727. Min Act: -0.0001

Data Index: 1267131 (C4 (Web Text))

Max Activating Token Index: 871

Text #3

Max Range: 1.5727. Min Range: -1.5727

Max Act: 1.3443. Min Act: -0.0001

Data Index: 381020 (C4 (Web Text))

Max Activating Token Index: 886

Text #4

Max Range: 1.5727. Min Range: -1.5727

Max Act: 1.2955. Min Act: -0.0001

Data Index: 268726 (C4 (Web Text))

Max Activating Token Index: 450

Text #5

Max Range: 1.5727. Min Range: -1.5727

Max Act: 1.1475. Min Act: -0.0001

Data Index: 1092791 (C4 (Web Text))

Max Activating Token Index: 419

Text #6

Max Range: 1.5727. Min Range: -1.5727

Max Act: 1.3364. Min Act: -0.0001

Data Index: 398409 (C4 (Web Text))

Max Activating Token Index: 229

Text #7

Max Range: 1.5727. Min Range: -1.5727

Max Act: 1.2352. Min Act: -0.0001

Data Index: 992525 (C4 (Web Text))

Max Activating Token Index: 582

Text #8

Max Range: 1.5727. Min Range: -1.5727

Max Act: 1.2428. Min Act: -0.0001

Data Index: 463632 (C4 (Web Text))

Max Activating Token Index: 336

Text #9

Max Range: 1.5727. Min Range: -1.5727

Max Act: 1.1675. Min Act: -0.0001

Data Index: 1118447 (C4 (Web Text))

Max Activating Token Index: 886

Text #10

Max Range: 1.5727. Min Range: -1.5727

Max Act: 1.1151. Min Act: -0.0001

Data Index: 883705 (C4 (Web Text))

Max Activating Token Index: 140

Text #11

Max Range: 1.5727. Min Range: -1.5727

Max Act: 1.1743. Min Act: -0.0001

Data Index: 1317296 (C4 (Web Text))

Max Activating Token Index: 211

Text #12

Max Range: 1.5727. Min Range: -1.5727

Max Act: 1.2072. Min Act: -0.0001

Data Index: 735969 (C4 (Web Text))

Max Activating Token Index: 535

Text #13

Max Range: 1.5727. Min Range: -1.5727

Max Act: 1.1831. Min Act: -0.0001

Data Index: 34217 (C4 (Web Text))

Max Activating Token Index: 765

Text #14

Max Range: 1.5727. Min Range: -1.5727

Max Act: 1.0839. Min Act: -0.0001

Data Index: 312898 (C4 (Web Text))

Max Activating Token Index: 656

Text #15

Max Range: 1.5727. Min Range: -1.5727

Max Act: 1.2313. Min Act: -0.0001

Data Index: 502782 (C4 (Web Text))

Max Activating Token Index: 184

Text #16

Max Range: 1.5727. Min Range: -1.5727

Max Act: 1.1880. Min Act: -0.0001

Data Index: 34559 (C4 (Web Text))

Max Activating Token Index: 936

Text #17

Max Range: 1.5727. Min Range: -1.5727

Max Act: 1.0793. Min Act: -0.0001

Data Index: 438054 (C4 (Web Text))

Max Activating Token Index: 175

Text #18

Max Range: 1.5727. Min Range: -1.5727

Max Act: 1.1794. Min Act: -0.0001

Data Index: 803962 (C4 (Web Text))

Max Activating Token Index: 762

Text #19

Max Range: 1.5727. Min Range: -1.5727

Max Act: 1.1370. Min Act: -0.0001

Data Index: 1344217 (C4 (Web Text))

Max Activating Token Index: 80