Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 2355 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.1788. Min Range: -0.1788

Max Act: 0.1788. Min Act: -0.0003

Data Index: 1316282 (C4 (Web Text))

Max Activating Token Index: 417

Text #1

Max Range: 0.1788. Min Range: -0.1788

Max Act: 0.1603. Min Act: -0.0003

Data Index: 754091 (C4 (Web Text))

Max Activating Token Index: 533

Text #2

Max Range: 0.1788. Min Range: -0.1788

Max Act: 0.1555. Min Act: -0.0003

Data Index: 102169 (C4 (Web Text))

Max Activating Token Index: 189

Text #3

Max Range: 0.1788. Min Range: -0.1788

Max Act: 0.1456. Min Act: -0.0002

Data Index: 1653932 (Python Code)

Max Activating Token Index: 487

Text #4

Max Range: 0.1788. Min Range: -0.1788

Max Act: 0.1367. Min Act: -0.0002

Data Index: 1385619 (Python Code)

Max Activating Token Index: 315

Text #5

Max Range: 0.1788. Min Range: -0.1788

Max Act: 0.1362. Min Act: -0.0002

Data Index: 647245 (C4 (Web Text))

Max Activating Token Index: 1011

Text #6

Max Range: 0.1788. Min Range: -0.1788

Max Act: 0.1302. Min Act: -0.0002

Data Index: 1512907 (Python Code)

Max Activating Token Index: 380

Text #7

Max Range: 0.1788. Min Range: -0.1788

Max Act: 0.1275. Min Act: -0.0002

Data Index: 1625907 (Python Code)

Max Activating Token Index: 178

Text #8

Max Range: 0.1788. Min Range: -0.1788

Max Act: 0.1255. Min Act: -0.0002

Data Index: 1655369 (Python Code)

Max Activating Token Index: 791

Text #9

Max Range: 0.1788. Min Range: -0.1788

Max Act: 0.1215. Min Act: -0.0002

Data Index: 1461770 (Python Code)

Max Activating Token Index: 43

Text #10

Max Range: 0.1788. Min Range: -0.1788

Max Act: 0.1212. Min Act: -0.0003

Data Index: 1805 (C4 (Web Text))

Max Activating Token Index: 637

Text #11

Max Range: 0.1788. Min Range: -0.1788

Max Act: 0.1175. Min Act: -0.0002

Data Index: 1406954 (Python Code)

Max Activating Token Index: 18

Text #12

Max Range: 0.1788. Min Range: -0.1788

Max Act: 0.1165. Min Act: -0.0003

Data Index: 611656 (C4 (Web Text))

Max Activating Token Index: 866

Text #13

Max Range: 0.1788. Min Range: -0.1788

Max Act: 0.1151. Min Act: -0.0002

Data Index: 1631053 (Python Code)

Max Activating Token Index: 314

Text #14

Max Range: 0.1788. Min Range: -0.1788

Max Act: 0.1151. Min Act: -0.0002

Data Index: 1602379 (Python Code)

Max Activating Token Index: 897

Text #15

Max Range: 0.1788. Min Range: -0.1788

Max Act: 0.1134. Min Act: -0.0003

Data Index: 1050367 (C4 (Web Text))

Max Activating Token Index: 395

Text #16

Max Range: 0.1788. Min Range: -0.1788

Max Act: 0.1130. Min Act: -0.0003

Data Index: 522608 (C4 (Web Text))

Max Activating Token Index: 117

Text #17

Max Range: 0.1788. Min Range: -0.1788

Max Act: 0.1104. Min Act: -0.0003

Data Index: 1341813 (C4 (Web Text))

Max Activating Token Index: 478

Text #18

Max Range: 0.1788. Min Range: -0.1788

Max Act: 0.1104. Min Act: -0.0002

Data Index: 15684 (C4 (Web Text))

Max Activating Token Index: 537

Text #19

Max Range: 0.1788. Min Range: -0.1788

Max Act: 0.1103. Min Act: -0.0002

Data Index: 1603190 (Python Code)

Max Activating Token Index: 592