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

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

Neuron 1612 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3471. Min Range: -0.3471

Max Act: 0.3471. Min Act: -0.0000

Data Index: 786227 (C4 (Web Text))

Max Activating Token Index: 671

Text #1

Max Range: 0.3471. Min Range: -0.3471

Max Act: 0.2679. Min Act: -0.0000

Data Index: 142595 (C4 (Web Text))

Max Activating Token Index: 394

Text #2

Max Range: 0.3471. Min Range: -0.3471

Max Act: 0.2410. Min Act: -0.0000

Data Index: 158196 (C4 (Web Text))

Max Activating Token Index: 124

Text #3

Max Range: 0.3471. Min Range: -0.3471

Max Act: 0.2665. Min Act: -0.0000

Data Index: 1073687 (C4 (Web Text))

Max Activating Token Index: 203

Text #4

Max Range: 0.3471. Min Range: -0.3471

Max Act: 0.2087. Min Act: -0.0000

Data Index: 1217272 (C4 (Web Text))

Max Activating Token Index: 729

Text #5

Max Range: 0.3471. Min Range: -0.3471

Max Act: 0.2372. Min Act: -0.0000

Data Index: 1265597 (C4 (Web Text))

Max Activating Token Index: 155

Text #6

Max Range: 0.3471. Min Range: -0.3471

Max Act: 0.2497. Min Act: -0.0000

Data Index: 619181 (C4 (Web Text))

Max Activating Token Index: 454

Text #7

Max Range: 0.3471. Min Range: -0.3471

Max Act: 0.2495. Min Act: -0.0000

Data Index: 961135 (C4 (Web Text))

Max Activating Token Index: 751

Text #8

Max Range: 0.3471. Min Range: -0.3471

Max Act: 0.2410. Min Act: -0.0000

Data Index: 319607 (C4 (Web Text))

Max Activating Token Index: 126

Text #9

Max Range: 0.3471. Min Range: -0.3471

Max Act: 0.2403. Min Act: -0.0000

Data Index: 355840 (C4 (Web Text))

Max Activating Token Index: 175

Text #10

Max Range: 0.3471. Min Range: -0.3471

Max Act: 0.2306. Min Act: -0.0000

Data Index: 400213 (C4 (Web Text))

Max Activating Token Index: 1019

Text #11

Max Range: 0.3471. Min Range: -0.3471

Max Act: 0.2180. Min Act: -0.0000

Data Index: 468696 (C4 (Web Text))

Max Activating Token Index: 12

Text #12

Max Range: 0.3471. Min Range: -0.3471

Max Act: 0.2371. Min Act: -0.0000

Data Index: 531125 (C4 (Web Text))

Max Activating Token Index: 582

Text #13

Max Range: 0.3471. Min Range: -0.3471

Max Act: 0.2313. Min Act: -0.0000

Data Index: 867144 (C4 (Web Text))

Max Activating Token Index: 52

Text #14

Max Range: 0.3471. Min Range: -0.3471

Max Act: 0.2306. Min Act: -0.0000

Data Index: 238515 (C4 (Web Text))

Max Activating Token Index: 466

Text #15

Max Range: 0.3471. Min Range: -0.3471

Max Act: 0.2378. Min Act: -0.0000

Data Index: 91066 (C4 (Web Text))

Max Activating Token Index: 1010

Text #16

Max Range: 0.3471. Min Range: -0.3471

Max Act: 0.2067. Min Act: -0.0000

Data Index: 901995 (C4 (Web Text))

Max Activating Token Index: 301

Text #17

Max Range: 0.3471. Min Range: -0.3471

Max Act: 0.2346. Min Act: -0.0000

Data Index: 478774 (C4 (Web Text))

Max Activating Token Index: 976

Text #18

Max Range: 0.3471. Min Range: -0.3471

Max Act: 0.2333. Min Act: -0.0000

Data Index: 338902 (C4 (Web Text))

Max Activating Token Index: 124

Text #19

Max Range: 0.3471. Min Range: -0.3471

Max Act: 0.2318. Min Act: -0.0000

Data Index: 328877 (C4 (Web Text))

Max Activating Token Index: 257