Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 4426 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.1622. Min Range: -0.1622

Max Act: 0.1622. Min Act: -0.0002

Data Index: 1064417 (C4 (Web Text))

Max Activating Token Index: 402

Text #1

Max Range: 0.1622. Min Range: -0.1622

Max Act: 0.1519. Min Act: -0.0002

Data Index: 414780 (C4 (Web Text))

Max Activating Token Index: 676

Text #2

Max Range: 0.1622. Min Range: -0.1622

Max Act: 0.1401. Min Act: -0.0002

Data Index: 89828 (C4 (Web Text))

Max Activating Token Index: 327

Text #3

Max Range: 0.1622. Min Range: -0.1622

Max Act: 0.1273. Min Act: -0.0002

Data Index: 307654 (C4 (Web Text))

Max Activating Token Index: 653

Text #4

Max Range: 0.1622. Min Range: -0.1622

Max Act: 0.1397. Min Act: -0.0002

Data Index: 67275 (C4 (Web Text))

Max Activating Token Index: 353

Text #5

Max Range: 0.1622. Min Range: -0.1622

Max Act: 0.1301. Min Act: -0.0002

Data Index: 475728 (C4 (Web Text))

Max Activating Token Index: 993

Text #6

Max Range: 0.1622. Min Range: -0.1622

Max Act: 0.1396. Min Act: -0.0002

Data Index: 826898 (C4 (Web Text))

Max Activating Token Index: 353

Text #7

Max Range: 0.1622. Min Range: -0.1622

Max Act: 0.1302. Min Act: -0.0002

Data Index: 27635 (C4 (Web Text))

Max Activating Token Index: 471

Text #8

Max Range: 0.1622. Min Range: -0.1622

Max Act: 0.1301. Min Act: -0.0002

Data Index: 414097 (C4 (Web Text))

Max Activating Token Index: 3

Text #9

Max Range: 0.1622. Min Range: -0.1622

Max Act: 0.1301. Min Act: -0.0002

Data Index: 434448 (C4 (Web Text))

Max Activating Token Index: 3

Text #10

Max Range: 0.1622. Min Range: -0.1622

Max Act: 0.1283. Min Act: -0.0002

Data Index: 398812 (C4 (Web Text))

Max Activating Token Index: 882

Text #11

Max Range: 0.1622. Min Range: -0.1622

Max Act: 0.1273. Min Act: -0.0002

Data Index: 890018 (C4 (Web Text))

Max Activating Token Index: 595

Text #12

Max Range: 0.1622. Min Range: -0.1622

Max Act: 0.1131. Min Act: -0.0002

Data Index: 1110557 (C4 (Web Text))

Max Activating Token Index: 439

Text #13

Max Range: 0.1622. Min Range: -0.1622

Max Act: 0.1338. Min Act: -0.0002

Data Index: 1056602 (C4 (Web Text))

Max Activating Token Index: 103

Text #14

Max Range: 0.1622. Min Range: -0.1622

Max Act: 0.1005. Min Act: -0.0002

Data Index: 1021218 (C4 (Web Text))

Max Activating Token Index: 628

Text #15

Max Range: 0.1622. Min Range: -0.1622

Max Act: 0.1140. Min Act: -0.0002

Data Index: 400138 (C4 (Web Text))

Max Activating Token Index: 267

Text #16

Max Range: 0.1622. Min Range: -0.1622

Max Act: 0.1190. Min Act: -0.0002

Data Index: 924089 (C4 (Web Text))

Max Activating Token Index: 644

Text #17

Max Range: 0.1622. Min Range: -0.1622

Max Act: 0.1061. Min Act: -0.0002

Data Index: 1034573 (C4 (Web Text))

Max Activating Token Index: 870

Text #18

Max Range: 0.1622. Min Range: -0.1622

Max Act: 0.1173. Min Act: -0.0002

Data Index: 30493 (C4 (Web Text))

Max Activating Token Index: 465

Text #19

Max Range: 0.1622. Min Range: -0.1622

Max Act: 0.1206. Min Act: -0.0002

Data Index: 916199 (C4 (Web Text))

Max Activating Token Index: 383