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

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

Neuron 2907 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3526. Min Range: -0.3526

Max Act: 0.3526. Min Act: -0.0000

Data Index: 694873 (C4 (Web Text))

Max Activating Token Index: 843

Text #1

Max Range: 0.3526. Min Range: -0.3526

Max Act: 0.2877. Min Act: -0.0000

Data Index: 87786 (C4 (Web Text))

Max Activating Token Index: 563

Text #2

Max Range: 0.3526. Min Range: -0.3526

Max Act: 0.2750. Min Act: -0.0000

Data Index: 46925 (C4 (Web Text))

Max Activating Token Index: 115

Text #3

Max Range: 0.3526. Min Range: -0.3526

Max Act: 0.2631. Min Act: -0.0000

Data Index: 551146 (C4 (Web Text))

Max Activating Token Index: 767

Text #4

Max Range: 0.3526. Min Range: -0.3526

Max Act: 0.2535. Min Act: -0.0000

Data Index: 471637 (C4 (Web Text))

Max Activating Token Index: 163

Text #5

Max Range: 0.3526. Min Range: -0.3526

Max Act: 0.2575. Min Act: -0.0000

Data Index: 703738 (C4 (Web Text))

Max Activating Token Index: 592

Text #6

Max Range: 0.3526. Min Range: -0.3526

Max Act: 0.2603. Min Act: -0.0000

Data Index: 119136 (C4 (Web Text))

Max Activating Token Index: 76

Text #7

Max Range: 0.3526. Min Range: -0.3526

Max Act: 0.2489. Min Act: -0.0000

Data Index: 272122 (C4 (Web Text))

Max Activating Token Index: 154

Text #8

Max Range: 0.3526. Min Range: -0.3526

Max Act: 0.2482. Min Act: -0.0000

Data Index: 144177 (C4 (Web Text))

Max Activating Token Index: 795

Text #9

Max Range: 0.3526. Min Range: -0.3526

Max Act: 0.2205. Min Act: -0.0000

Data Index: 1564887 (Python Code)

Max Activating Token Index: 863

Text #10

Max Range: 0.3526. Min Range: -0.3526

Max Act: 0.2530. Min Act: -0.0000

Data Index: 78007 (C4 (Web Text))

Max Activating Token Index: 319

Text #11

Max Range: 0.3526. Min Range: -0.3526

Max Act: 0.2404. Min Act: -0.0000

Data Index: 835204 (C4 (Web Text))

Max Activating Token Index: 379

Text #12

Max Range: 0.3526. Min Range: -0.3526

Max Act: 0.2391. Min Act: -0.0000

Data Index: 1535410 (Python Code)

Max Activating Token Index: 321

Text #13

Max Range: 0.3526. Min Range: -0.3526

Max Act: 0.2428. Min Act: -0.0000

Data Index: 234045 (C4 (Web Text))

Max Activating Token Index: 435

Text #14

Max Range: 0.3526. Min Range: -0.3526

Max Act: 0.2362. Min Act: -0.0000

Data Index: 365427 (C4 (Web Text))

Max Activating Token Index: 558

Text #15

Max Range: 0.3526. Min Range: -0.3526

Max Act: 0.2262. Min Act: -0.0000

Data Index: 145212 (C4 (Web Text))

Max Activating Token Index: 248

Text #16

Max Range: 0.3526. Min Range: -0.3526

Max Act: 0.2384. Min Act: -0.0000

Data Index: 1447326 (Python Code)

Max Activating Token Index: 39

Text #17

Max Range: 0.3526. Min Range: -0.3526

Max Act: 0.2536. Min Act: -0.0000

Data Index: 741274 (C4 (Web Text))

Max Activating Token Index: 309

Text #18

Max Range: 0.3526. Min Range: -0.3526

Max Act: 0.2309. Min Act: -0.0000

Data Index: 863879 (C4 (Web Text))

Max Activating Token Index: 909

Text #19

Max Range: 0.3526. Min Range: -0.3526

Max Act: 0.2350. Min Act: -0.0000

Data Index: 1012712 (C4 (Web Text))

Max Activating Token Index: 820