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

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

Neuron 4010 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3339. Min Range: -0.3339

Max Act: 0.3339. Min Act: -0.0000

Data Index: 1224145 (C4 (Web Text))

Max Activating Token Index: 364

Text #1

Max Range: 0.3339. Min Range: -0.3339

Max Act: 0.2948. Min Act: -0.0000

Data Index: 451742 (C4 (Web Text))

Max Activating Token Index: 385

Text #2

Max Range: 0.3339. Min Range: -0.3339

Max Act: 0.2658. Min Act: -0.0001

Data Index: 1184649 (C4 (Web Text))

Max Activating Token Index: 829

Text #3

Max Range: 0.3339. Min Range: -0.3339

Max Act: 0.2607. Min Act: -0.0000

Data Index: 223660 (C4 (Web Text))

Max Activating Token Index: 371

Text #4

Max Range: 0.3339. Min Range: -0.3339

Max Act: 0.2629. Min Act: -0.0000

Data Index: 376271 (C4 (Web Text))

Max Activating Token Index: 484

Text #5

Max Range: 0.3339. Min Range: -0.3339

Max Act: 0.2559. Min Act: -0.0000

Data Index: 620911 (C4 (Web Text))

Max Activating Token Index: 219

Text #6

Max Range: 0.3339. Min Range: -0.3339

Max Act: 0.2387. Min Act: -0.0000

Data Index: 292877 (C4 (Web Text))

Max Activating Token Index: 702

Text #7

Max Range: 0.3339. Min Range: -0.3339

Max Act: 0.2451. Min Act: -0.0000

Data Index: 1105211 (C4 (Web Text))

Max Activating Token Index: 716

Text #8

Max Range: 0.3339. Min Range: -0.3339

Max Act: 0.2505. Min Act: -0.0000

Data Index: 1205123 (C4 (Web Text))

Max Activating Token Index: 688

Text #9

Max Range: 0.3339. Min Range: -0.3339

Max Act: 0.2453. Min Act: -0.0001

Data Index: 891377 (C4 (Web Text))

Max Activating Token Index: 110

Text #10

Max Range: 0.3339. Min Range: -0.3339

Max Act: 0.2523. Min Act: -0.0000

Data Index: 964774 (C4 (Web Text))

Max Activating Token Index: 732

Text #11

Max Range: 0.3339. Min Range: -0.3339

Max Act: 0.2427. Min Act: -0.0000

Data Index: 707541 (C4 (Web Text))

Max Activating Token Index: 548

Text #12

Max Range: 0.3339. Min Range: -0.3339

Max Act: 0.2408. Min Act: -0.0000

Data Index: 81952 (C4 (Web Text))

Max Activating Token Index: 424

Text #13

Max Range: 0.3339. Min Range: -0.3339

Max Act: 0.2346. Min Act: -0.0000

Data Index: 1286215 (C4 (Web Text))

Max Activating Token Index: 788

Text #14

Max Range: 0.3339. Min Range: -0.3339

Max Act: 0.2408. Min Act: -0.0000

Data Index: 688279 (C4 (Web Text))

Max Activating Token Index: 896

Text #15

Max Range: 0.3339. Min Range: -0.3339

Max Act: 0.2339. Min Act: -0.0000

Data Index: 509012 (C4 (Web Text))

Max Activating Token Index: 111

Text #16

Max Range: 0.3339. Min Range: -0.3339

Max Act: 0.2324. Min Act: -0.0001

Data Index: 619717 (C4 (Web Text))

Max Activating Token Index: 296

Text #17

Max Range: 0.3339. Min Range: -0.3339

Max Act: 0.2283. Min Act: -0.0000

Data Index: 713652 (C4 (Web Text))

Max Activating Token Index: 971

Text #18

Max Range: 0.3339. Min Range: -0.3339

Max Act: 0.2382. Min Act: -0.0000

Data Index: 293037 (C4 (Web Text))

Max Activating Token Index: 565

Text #19

Max Range: 0.3339. Min Range: -0.3339

Max Act: 0.2231. Min Act: -0.0000

Data Index: 27573 (C4 (Web Text))

Max Activating Token Index: 386