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

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

Neuron 1117 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.8423. Min Range: -2.8423

Max Act: 2.8423. Min Act: -0.0000

Data Index: 585044 (C4 (Web Text))

Max Activating Token Index: 294

Text #1

Max Range: 2.8423. Min Range: -2.8423

Max Act: 2.7064. Min Act: -0.0000

Data Index: 268408 (C4 (Web Text))

Max Activating Token Index: 381

Text #2

Max Range: 2.8423. Min Range: -2.8423

Max Act: 2.5667. Min Act: -0.0000

Data Index: 268471 (C4 (Web Text))

Max Activating Token Index: 352

Text #3

Max Range: 2.8423. Min Range: -2.8423

Max Act: 2.6958. Min Act: -0.0000

Data Index: 379508 (C4 (Web Text))

Max Activating Token Index: 237

Text #4

Max Range: 2.8423. Min Range: -2.8423

Max Act: 2.6990. Min Act: -0.0000

Data Index: 1105326 (C4 (Web Text))

Max Activating Token Index: 415

Text #5

Max Range: 2.8423. Min Range: -2.8423

Max Act: 2.5528. Min Act: -0.0000

Data Index: 1240188 (C4 (Web Text))

Max Activating Token Index: 298

Text #6

Max Range: 2.8423. Min Range: -2.8423

Max Act: 2.6918. Min Act: -0.0000

Data Index: 1044012 (C4 (Web Text))

Max Activating Token Index: 291

Text #7

Max Range: 2.8423. Min Range: -2.8423

Max Act: 2.7007. Min Act: -0.0000

Data Index: 136795 (C4 (Web Text))

Max Activating Token Index: 439

Text #8

Max Range: 2.8423. Min Range: -2.8423

Max Act: 2.6859. Min Act: -0.0000

Data Index: 9187 (C4 (Web Text))

Max Activating Token Index: 335

Text #9

Max Range: 2.8423. Min Range: -2.8423

Max Act: 2.5557. Min Act: -0.0000

Data Index: 348670 (C4 (Web Text))

Max Activating Token Index: 224

Text #10

Max Range: 2.8423. Min Range: -2.8423

Max Act: 2.5534. Min Act: -0.0000

Data Index: 422780 (C4 (Web Text))

Max Activating Token Index: 307

Text #11

Max Range: 2.8423. Min Range: -2.8423

Max Act: 2.6814. Min Act: -0.0000

Data Index: 948255 (C4 (Web Text))

Max Activating Token Index: 373

Text #12

Max Range: 2.8423. Min Range: -2.8423

Max Act: 2.5443. Min Act: -0.0000

Data Index: 1344668 (C4 (Web Text))

Max Activating Token Index: 295

Text #13

Max Range: 2.8423. Min Range: -2.8423

Max Act: 2.6872. Min Act: -0.0000

Data Index: 1271129 (C4 (Web Text))

Max Activating Token Index: 579

Text #14

Max Range: 2.8423. Min Range: -2.8423

Max Act: 2.6718. Min Act: -0.0000

Data Index: 89420 (C4 (Web Text))

Max Activating Token Index: 248

Text #15

Max Range: 2.8423. Min Range: -2.8423

Max Act: 2.5571. Min Act: -0.0000

Data Index: 693904 (C4 (Web Text))

Max Activating Token Index: 401

Text #16

Max Range: 2.8423. Min Range: -2.8423

Max Act: 2.6983. Min Act: -0.0000

Data Index: 1044061 (C4 (Web Text))

Max Activating Token Index: 167

Text #17

Max Range: 2.8423. Min Range: -2.8423

Max Act: 2.8158. Min Act: -0.0000

Data Index: 1022734 (C4 (Web Text))

Max Activating Token Index: 171

Text #18

Max Range: 2.8423. Min Range: -2.8423

Max Act: 2.6836. Min Act: -0.0000

Data Index: 117938 (C4 (Web Text))

Max Activating Token Index: 307

Text #19

Max Range: 2.8423. Min Range: -2.8423

Max Act: 2.6745. Min Act: -0.0000

Data Index: 181438 (C4 (Web Text))

Max Activating Token Index: 264