Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 2750 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.3642. Min Range: -0.3642

Max Act: 0.3642. Min Act: -0.0001

Data Index: 437888 (C4 (Web Text))

Max Activating Token Index: 885

Text #1

Max Range: 0.3642. Min Range: -0.3642

Max Act: 0.2682. Min Act: -0.0001

Data Index: 920720 (C4 (Web Text))

Max Activating Token Index: 133

Text #2

Max Range: 0.3642. Min Range: -0.3642

Max Act: 0.2865. Min Act: -0.0001

Data Index: 628479 (C4 (Web Text))

Max Activating Token Index: 928

Text #3

Max Range: 0.3642. Min Range: -0.3642

Max Act: 0.2952. Min Act: -0.0001

Data Index: 1172177 (C4 (Web Text))

Max Activating Token Index: 85

Text #4

Max Range: 0.3642. Min Range: -0.3642

Max Act: 0.2535. Min Act: -0.0001

Data Index: 535366 (C4 (Web Text))

Max Activating Token Index: 522

Text #5

Max Range: 0.3642. Min Range: -0.3642

Max Act: 0.2553. Min Act: -0.0001

Data Index: 192418 (C4 (Web Text))

Max Activating Token Index: 357

Text #6

Max Range: 0.3642. Min Range: -0.3642

Max Act: 0.2315. Min Act: -0.0001

Data Index: 1213185 (C4 (Web Text))

Max Activating Token Index: 353

Text #7

Max Range: 0.3642. Min Range: -0.3642

Max Act: 0.2433. Min Act: -0.0001

Data Index: 1023333 (C4 (Web Text))

Max Activating Token Index: 497

Text #8

Max Range: 0.3642. Min Range: -0.3642

Max Act: 0.2084. Min Act: -0.0001

Data Index: 1289519 (C4 (Web Text))

Max Activating Token Index: 317

Text #9

Max Range: 0.3642. Min Range: -0.3642

Max Act: 0.2353. Min Act: -0.0001

Data Index: 1273224 (C4 (Web Text))

Max Activating Token Index: 920

Text #10

Max Range: 0.3642. Min Range: -0.3642

Max Act: 0.2557. Min Act: -0.0001

Data Index: 70938 (C4 (Web Text))

Max Activating Token Index: 77

Text #11

Max Range: 0.3642. Min Range: -0.3642

Max Act: 0.2446. Min Act: -0.0001

Data Index: 714764 (C4 (Web Text))

Max Activating Token Index: 956

Text #12

Max Range: 0.3642. Min Range: -0.3642

Max Act: 0.2297. Min Act: -0.0001

Data Index: 50159 (C4 (Web Text))

Max Activating Token Index: 240

Text #13

Max Range: 0.3642. Min Range: -0.3642

Max Act: 0.2495. Min Act: -0.0001

Data Index: 417626 (C4 (Web Text))

Max Activating Token Index: 534

Text #14

Max Range: 0.3642. Min Range: -0.3642

Max Act: 0.2001. Min Act: -0.0001

Data Index: 1316884 (C4 (Web Text))

Max Activating Token Index: 888

Text #15

Max Range: 0.3642. Min Range: -0.3642

Max Act: 0.2252. Min Act: -0.0001

Data Index: 291010 (C4 (Web Text))

Max Activating Token Index: 888

Text #16

Max Range: 0.3642. Min Range: -0.3642

Max Act: 0.2305. Min Act: -0.0001

Data Index: 790316 (C4 (Web Text))

Max Activating Token Index: 788

Text #17

Max Range: 0.3642. Min Range: -0.3642

Max Act: 0.2179. Min Act: -0.0001

Data Index: 766812 (C4 (Web Text))

Max Activating Token Index: 29

Text #18

Max Range: 0.3642. Min Range: -0.3642

Max Act: 0.2311. Min Act: -0.0001

Data Index: 1329407 (C4 (Web Text))

Max Activating Token Index: 859

Text #19

Max Range: 0.3642. Min Range: -0.3642

Max Act: 0.2370. Min Act: -0.0001

Data Index: 1158043 (C4 (Web Text))

Max Activating Token Index: 939