Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 1604 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 4.2289. Min Range: -4.2289

Max Act: 4.2289. Min Act: -0.0000

Data Index: 600880 (C4 (Web Text))

Max Activating Token Index: 323

Text #1

Max Range: 4.2289. Min Range: -4.2289

Max Act: 3.6990. Min Act: -0.0000

Data Index: 296103 (C4 (Web Text))

Max Activating Token Index: 609

Text #2

Max Range: 4.2289. Min Range: -4.2289

Max Act: 3.6060. Min Act: -0.0000

Data Index: 445768 (C4 (Web Text))

Max Activating Token Index: 714

Text #3

Max Range: 4.2289. Min Range: -4.2289

Max Act: 3.4265. Min Act: -0.0000

Data Index: 798004 (C4 (Web Text))

Max Activating Token Index: 862

Text #4

Max Range: 4.2289. Min Range: -4.2289

Max Act: 3.5959. Min Act: -0.0000

Data Index: 1179095 (C4 (Web Text))

Max Activating Token Index: 919

Text #5

Max Range: 4.2289. Min Range: -4.2289

Max Act: 3.6723. Min Act: -0.0000

Data Index: 377033 (C4 (Web Text))

Max Activating Token Index: 568

Text #6

Max Range: 4.2289. Min Range: -4.2289

Max Act: 3.4859. Min Act: -0.0000

Data Index: 992108 (C4 (Web Text))

Max Activating Token Index: 922

Text #7

Max Range: 4.2289. Min Range: -4.2289

Max Act: 3.4302. Min Act: -0.0000

Data Index: 960033 (C4 (Web Text))

Max Activating Token Index: 109

Text #8

Max Range: 4.2289. Min Range: -4.2289

Max Act: 3.2427. Min Act: -0.0000

Data Index: 530153 (C4 (Web Text))

Max Activating Token Index: 700

Text #9

Max Range: 4.2289. Min Range: -4.2289

Max Act: 3.2560. Min Act: -0.0000

Data Index: 593960 (C4 (Web Text))

Max Activating Token Index: 481

Text #10

Max Range: 4.2289. Min Range: -4.2289

Max Act: 3.3794. Min Act: -0.0000

Data Index: 142150 (C4 (Web Text))

Max Activating Token Index: 123

Text #11

Max Range: 4.2289. Min Range: -4.2289

Max Act: 3.3474. Min Act: -0.0000

Data Index: 987451 (C4 (Web Text))

Max Activating Token Index: 509

Text #12

Max Range: 4.2289. Min Range: -4.2289

Max Act: 3.3323. Min Act: -0.0000

Data Index: 819481 (C4 (Web Text))

Max Activating Token Index: 167

Text #13

Max Range: 4.2289. Min Range: -4.2289

Max Act: 3.3925. Min Act: -0.0000

Data Index: 626325 (C4 (Web Text))

Max Activating Token Index: 810

Text #14

Max Range: 4.2289. Min Range: -4.2289

Max Act: 3.3286. Min Act: -0.0000

Data Index: 749681 (C4 (Web Text))

Max Activating Token Index: 829

Text #15

Max Range: 4.2289. Min Range: -4.2289

Max Act: 3.5957. Min Act: -0.0000

Data Index: 685075 (C4 (Web Text))

Max Activating Token Index: 875

Text #16

Max Range: 4.2289. Min Range: -4.2289

Max Act: 3.2707. Min Act: -0.0000

Data Index: 657884 (C4 (Web Text))

Max Activating Token Index: 558

Text #17

Max Range: 4.2289. Min Range: -4.2289

Max Act: 3.4408. Min Act: -0.0000

Data Index: 1343838 (C4 (Web Text))

Max Activating Token Index: 78

Text #18

Max Range: 4.2289. Min Range: -4.2289

Max Act: 3.3581. Min Act: -0.0000

Data Index: 1028579 (C4 (Web Text))

Max Activating Token Index: 383

Text #19

Max Range: 4.2289. Min Range: -4.2289

Max Act: 3.2183. Min Act: -0.0000

Data Index: 1254840 (C4 (Web Text))

Max Activating Token Index: 453