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

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

Neuron 712 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Click the toggle to see the full text!

Text #0

Max Range: 1.2023. Min Range: -1.2023

Max Act: 1.2023. Min Act: -0.0002

Data Index: 71975 (C4 (Web Text))

Max Activating Token Index: 251

Text #1

Max Range: 1.2023. Min Range: -1.2023

Max Act: 1.1490. Min Act: -0.0002

Data Index: 1024292 (C4 (Web Text))

Max Activating Token Index: 346

Text #2

Max Range: 1.2023. Min Range: -1.2023

Max Act: 1.1052. Min Act: -0.0002

Data Index: 21540 (C4 (Web Text))

Max Activating Token Index: 762

Text #3

Max Range: 1.2023. Min Range: -1.2023

Max Act: 1.0765. Min Act: -0.0003

Data Index: 754703 (C4 (Web Text))

Max Activating Token Index: 433

Text #4

Max Range: 1.2023. Min Range: -1.2023

Max Act: 1.0787. Min Act: -0.0002

Data Index: 540001 (C4 (Web Text))

Max Activating Token Index: 580

Text #5

Max Range: 1.2023. Min Range: -1.2023

Max Act: 1.0558. Min Act: -0.0002

Data Index: 612492 (C4 (Web Text))

Max Activating Token Index: 192

Text #6

Max Range: 1.2023. Min Range: -1.2023

Max Act: 1.0784. Min Act: -0.0002

Data Index: 3021 (C4 (Web Text))

Max Activating Token Index: 261

Text #7

Max Range: 1.2023. Min Range: -1.2023

Max Act: 1.0510. Min Act: -0.0002

Data Index: 652183 (C4 (Web Text))

Max Activating Token Index: 278

Text #8

Max Range: 1.2023. Min Range: -1.2023

Max Act: 1.0567. Min Act: -0.0003

Data Index: 1047258 (C4 (Web Text))

Max Activating Token Index: 82

Text #9

Max Range: 1.2023. Min Range: -1.2023

Max Act: 1.0519. Min Act: -0.0003

Data Index: 52554 (C4 (Web Text))

Max Activating Token Index: 667

Text #10

Max Range: 1.2023. Min Range: -1.2023

Max Act: 1.0223. Min Act: -0.0003

Data Index: 530826 (C4 (Web Text))

Max Activating Token Index: 455

Text #11

Max Range: 1.2023. Min Range: -1.2023

Max Act: 1.0246. Min Act: -0.0002

Data Index: 1268277 (C4 (Web Text))

Max Activating Token Index: 143

Text #12

Max Range: 1.2023. Min Range: -1.2023

Max Act: 1.0400. Min Act: -0.0002

Data Index: 561046 (C4 (Web Text))

Max Activating Token Index: 45

Text #13

Max Range: 1.2023. Min Range: -1.2023

Max Act: 1.0200. Min Act: -0.0002

Data Index: 421960 (C4 (Web Text))

Max Activating Token Index: 418

Text #14

Max Range: 1.2023. Min Range: -1.2023

Max Act: 1.0108. Min Act: -0.0002

Data Index: 759735 (C4 (Web Text))

Max Activating Token Index: 250

Text #15

Max Range: 1.2023. Min Range: -1.2023

Max Act: 1.0262. Min Act: -0.0003

Data Index: 1338318 (C4 (Web Text))

Max Activating Token Index: 213

Text #16

Max Range: 1.2023. Min Range: -1.2023

Max Act: 0.9993. Min Act: -0.0002

Data Index: 821281 (C4 (Web Text))

Max Activating Token Index: 366

Text #17

Max Range: 1.2023. Min Range: -1.2023

Max Act: 0.9975. Min Act: -0.0002

Data Index: 1122564 (C4 (Web Text))

Max Activating Token Index: 200

Text #18

Max Range: 1.2023. Min Range: -1.2023

Max Act: 1.0035. Min Act: -0.0002

Data Index: 1258894 (C4 (Web Text))

Max Activating Token Index: 342

Text #19

Max Range: 1.2023. Min Range: -1.2023

Max Act: 1.0056. Min Act: -0.0002

Data Index: 1343353 (C4 (Web Text))

Max Activating Token Index: 510