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

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

Neuron 521 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: 0.0414. Min Range: -0.0414

Max Act: 0.0395. Min Act: -0.0002

Data Index: 228314 (C4 (Web Text))

Max Activating Token Index: 24

Text #1

Max Range: 0.0414. Min Range: -0.0414

Max Act: 0.0388. Min Act: -0.0002

Data Index: 136958 (C4 (Web Text))

Max Activating Token Index: 515

Text #2

Max Range: 0.0414. Min Range: -0.0414

Max Act: 0.0414. Min Act: -0.0002

Data Index: 1484291 (Python Code)

Max Activating Token Index: 229

Text #3

Max Range: 0.0414. Min Range: -0.0414

Max Act: 0.0395. Min Act: -0.0002

Data Index: 1194736 (C4 (Web Text))

Max Activating Token Index: 561

Text #4

Max Range: 0.0414. Min Range: -0.0414

Max Act: 0.0369. Min Act: -0.0002

Data Index: 996933 (C4 (Web Text))

Max Activating Token Index: 666

Text #5

Max Range: 0.0414. Min Range: -0.0414

Max Act: 0.0394. Min Act: -0.0002

Data Index: 914609 (C4 (Web Text))

Max Activating Token Index: 133

Text #6

Max Range: 0.0414. Min Range: -0.0414

Max Act: 0.0361. Min Act: -0.0002

Data Index: 1415003 (Python Code)

Max Activating Token Index: 297

Text #7

Max Range: 0.0414. Min Range: -0.0414

Max Act: 0.0337. Min Act: -0.0002

Data Index: 1072373 (C4 (Web Text))

Max Activating Token Index: 232

Text #8

Max Range: 0.0414. Min Range: -0.0414

Max Act: 0.0314. Min Act: -0.0002

Data Index: 1431960 (Python Code)

Max Activating Token Index: 113

Text #9

Max Range: 0.0414. Min Range: -0.0414

Max Act: 0.0323. Min Act: -0.0002

Data Index: 1124247 (C4 (Web Text))

Max Activating Token Index: 340

Text #10

Max Range: 0.0414. Min Range: -0.0414

Max Act: 0.0324. Min Act: -0.0002

Data Index: 1205049 (C4 (Web Text))

Max Activating Token Index: 942

Text #11

Max Range: 0.0414. Min Range: -0.0414

Max Act: 0.0290. Min Act: -0.0002

Data Index: 546114 (C4 (Web Text))

Max Activating Token Index: 941

Text #12

Max Range: 0.0414. Min Range: -0.0414

Max Act: 0.0314. Min Act: -0.0002

Data Index: 1084549 (C4 (Web Text))

Max Activating Token Index: 419

Text #13

Max Range: 0.0414. Min Range: -0.0414

Max Act: 0.0327. Min Act: -0.0002

Data Index: 559890 (C4 (Web Text))

Max Activating Token Index: 1012

Text #14

Max Range: 0.0414. Min Range: -0.0414

Max Act: 0.0314. Min Act: -0.0002

Data Index: 359170 (C4 (Web Text))

Max Activating Token Index: 143

Text #15

Max Range: 0.0414. Min Range: -0.0414

Max Act: 0.0311. Min Act: -0.0002

Data Index: 643052 (C4 (Web Text))

Max Activating Token Index: 153

Text #16

Max Range: 0.0414. Min Range: -0.0414

Max Act: 0.0313. Min Act: -0.0002

Data Index: 1375023 (Python Code)

Max Activating Token Index: 969

Text #17

Max Range: 0.0414. Min Range: -0.0414

Max Act: 0.0309. Min Act: -0.0002

Data Index: 707888 (C4 (Web Text))

Max Activating Token Index: 637

Text #18

Max Range: 0.0414. Min Range: -0.0414

Max Act: 0.0316. Min Act: -0.0002

Data Index: 150698 (C4 (Web Text))

Max Activating Token Index: 184

Text #19

Max Range: 0.0414. Min Range: -0.0414

Max Act: 0.0326. Min Act: -0.0002

Data Index: 320727 (C4 (Web Text))

Max Activating Token Index: 17