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

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

Neuron 1836 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.9988. Min Range: -1.9988

Max Act: 1.9988. Min Act: -0.0003

Data Index: 30867 (C4 (Web Text))

Max Activating Token Index: 37

Text #1

Max Range: 1.9988. Min Range: -1.9988

Max Act: 1.5923. Min Act: -0.0003

Data Index: 718282 (C4 (Web Text))

Max Activating Token Index: 291

Text #2

Max Range: 1.9988. Min Range: -1.9988

Max Act: 1.7442. Min Act: -0.0003

Data Index: 596410 (C4 (Web Text))

Max Activating Token Index: 103

Text #3

Max Range: 1.9988. Min Range: -1.9988

Max Act: 1.8994. Min Act: -0.0003

Data Index: 1255857 (C4 (Web Text))

Max Activating Token Index: 646

Text #4

Max Range: 1.9988. Min Range: -1.9988

Max Act: 1.5471. Min Act: -0.0003

Data Index: 277874 (C4 (Web Text))

Max Activating Token Index: 313

Text #5

Max Range: 1.9988. Min Range: -1.9988

Max Act: 1.6253. Min Act: -0.0003

Data Index: 1098374 (C4 (Web Text))

Max Activating Token Index: 113

Text #6

Max Range: 1.9988. Min Range: -1.9988

Max Act: 1.7728. Min Act: -0.0003

Data Index: 336339 (C4 (Web Text))

Max Activating Token Index: 357

Text #7

Max Range: 1.9988. Min Range: -1.9988

Max Act: 1.4856. Min Act: -0.0003

Data Index: 130290 (C4 (Web Text))

Max Activating Token Index: 374

Text #8

Max Range: 1.9988. Min Range: -1.9988

Max Act: 1.5813. Min Act: -0.0003

Data Index: 1231959 (C4 (Web Text))

Max Activating Token Index: 156

Text #9

Max Range: 1.9988. Min Range: -1.9988

Max Act: 1.1389. Min Act: -0.0003

Data Index: 1214607 (C4 (Web Text))

Max Activating Token Index: 609

Text #10

Max Range: 1.9988. Min Range: -1.9988

Max Act: 1.4936. Min Act: -0.0003

Data Index: 164214 (C4 (Web Text))

Max Activating Token Index: 10

Text #11

Max Range: 1.9988. Min Range: -1.9988

Max Act: 1.4893. Min Act: -0.0003

Data Index: 1077429 (C4 (Web Text))

Max Activating Token Index: 704

Text #12

Max Range: 1.9988. Min Range: -1.9988

Max Act: 1.5213. Min Act: -0.0003

Data Index: 1247213 (C4 (Web Text))

Max Activating Token Index: 154

Text #13

Max Range: 1.9988. Min Range: -1.9988

Max Act: 1.5980. Min Act: -0.0003

Data Index: 225816 (C4 (Web Text))

Max Activating Token Index: 480

Text #14

Max Range: 1.9988. Min Range: -1.9988

Max Act: 1.5962. Min Act: -0.0003

Data Index: 1272996 (C4 (Web Text))

Max Activating Token Index: 543

Text #15

Max Range: 1.9988. Min Range: -1.9988

Max Act: 1.4266. Min Act: -0.0003

Data Index: 479047 (C4 (Web Text))

Max Activating Token Index: 654

Text #16

Max Range: 1.9988. Min Range: -1.9988

Max Act: 1.3441. Min Act: -0.0003

Data Index: 334370 (C4 (Web Text))

Max Activating Token Index: 999

Text #17

Max Range: 1.9988. Min Range: -1.9988

Max Act: 1.5034. Min Act: -0.0003

Data Index: 272785 (C4 (Web Text))

Max Activating Token Index: 32

Text #18

Max Range: 1.9988. Min Range: -1.9988

Max Act: 1.4195. Min Act: -0.0003

Data Index: 362346 (C4 (Web Text))

Max Activating Token Index: 201

Text #19

Max Range: 1.9988. Min Range: -1.9988

Max Act: 1.4971. Min Act: -0.0003

Data Index: 1169326 (C4 (Web Text))

Max Activating Token Index: 866