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

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

Neuron 1566 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.2363. Min Range: -1.2363

Max Act: 1.2213. Min Act: -0.0000

Data Index: 277737 (C4 (Web Text))

Max Activating Token Index: 393

Text #1

Max Range: 1.2363. Min Range: -1.2363

Max Act: 1.2363. Min Act: -0.0000

Data Index: 980783 (C4 (Web Text))

Max Activating Token Index: 349

Text #2

Max Range: 1.2363. Min Range: -1.2363

Max Act: 1.2034. Min Act: -0.0000

Data Index: 1259837 (C4 (Web Text))

Max Activating Token Index: 544

Text #3

Max Range: 1.2363. Min Range: -1.2363

Max Act: 1.0715. Min Act: -0.0000

Data Index: 1507866 (Python Code)

Max Activating Token Index: 138

Text #4

Max Range: 1.2363. Min Range: -1.2363

Max Act: 1.0658. Min Act: -0.0000

Data Index: 799789 (C4 (Web Text))

Max Activating Token Index: 958

Text #5

Max Range: 1.2363. Min Range: -1.2363

Max Act: 1.1223. Min Act: -0.0000

Data Index: 839179 (C4 (Web Text))

Max Activating Token Index: 650

Text #6

Max Range: 1.2363. Min Range: -1.2363

Max Act: 1.1138. Min Act: -0.0000

Data Index: 1138243 (C4 (Web Text))

Max Activating Token Index: 883

Text #7

Max Range: 1.2363. Min Range: -1.2363

Max Act: 1.1872. Min Act: -0.0000

Data Index: 823417 (C4 (Web Text))

Max Activating Token Index: 366

Text #8

Max Range: 1.2363. Min Range: -1.2363

Max Act: 1.0764. Min Act: -0.0000

Data Index: 1355701 (C4 (Web Text))

Max Activating Token Index: 626

Text #9

Max Range: 1.2363. Min Range: -1.2363

Max Act: 1.0310. Min Act: -0.0000

Data Index: 1583290 (Python Code)

Max Activating Token Index: 19

Text #10

Max Range: 1.2363. Min Range: -1.2363

Max Act: 1.0752. Min Act: -0.0000

Data Index: 963013 (C4 (Web Text))

Max Activating Token Index: 302

Text #11

Max Range: 1.2363. Min Range: -1.2363

Max Act: 1.0088. Min Act: -0.0000

Data Index: 239577 (C4 (Web Text))

Max Activating Token Index: 482

Text #12

Max Range: 1.2363. Min Range: -1.2363

Max Act: 1.0324. Min Act: -0.0000

Data Index: 1477414 (Python Code)

Max Activating Token Index: 199

Text #13

Max Range: 1.2363. Min Range: -1.2363

Max Act: 0.9583. Min Act: -0.0000

Data Index: 293869 (C4 (Web Text))

Max Activating Token Index: 360

Text #14

Max Range: 1.2363. Min Range: -1.2363

Max Act: 0.9202. Min Act: -0.0000

Data Index: 231106 (C4 (Web Text))

Max Activating Token Index: 870

Text #15

Max Range: 1.2363. Min Range: -1.2363

Max Act: 0.9283. Min Act: -0.0000

Data Index: 796293 (C4 (Web Text))

Max Activating Token Index: 555

Text #16

Max Range: 1.2363. Min Range: -1.2363

Max Act: 0.9150. Min Act: -0.0000

Data Index: 1480870 (Python Code)

Max Activating Token Index: 262

Text #17

Max Range: 1.2363. Min Range: -1.2363

Max Act: 0.9250. Min Act: -0.0000

Data Index: 853141 (C4 (Web Text))

Max Activating Token Index: 695

Text #18

Max Range: 1.2363. Min Range: -1.2363

Max Act: 0.8912. Min Act: -0.0000

Data Index: 1557381 (Python Code)

Max Activating Token Index: 566

Text #19

Max Range: 1.2363. Min Range: -1.2363

Max Act: 0.8419. Min Act: -0.0000

Data Index: 1401402 (Python Code)

Max Activating Token Index: 957