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

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

Neuron 1290 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.3517. Min Range: -4.3517

Max Act: 4.3517. Min Act: -0.0000

Data Index: 427133 (C4 (Web Text))

Max Activating Token Index: 306

Text #1

Max Range: 4.3517. Min Range: -4.3517

Max Act: 3.8906. Min Act: -0.0000

Data Index: 158085 (C4 (Web Text))

Max Activating Token Index: 814

Text #2

Max Range: 4.3517. Min Range: -4.3517

Max Act: 3.9229. Min Act: -0.0000

Data Index: 568772 (C4 (Web Text))

Max Activating Token Index: 705

Text #3

Max Range: 4.3517. Min Range: -4.3517

Max Act: 3.6274. Min Act: -0.0000

Data Index: 1113836 (C4 (Web Text))

Max Activating Token Index: 153

Text #4

Max Range: 4.3517. Min Range: -4.3517

Max Act: 3.7995. Min Act: -0.0000

Data Index: 457408 (C4 (Web Text))

Max Activating Token Index: 810

Text #5

Max Range: 4.3517. Min Range: -4.3517

Max Act: 3.4587. Min Act: -0.0000

Data Index: 200112 (C4 (Web Text))

Max Activating Token Index: 978

Text #6

Max Range: 4.3517. Min Range: -4.3517

Max Act: 3.4971. Min Act: -0.0000

Data Index: 1098315 (C4 (Web Text))

Max Activating Token Index: 233

Text #7

Max Range: 4.3517. Min Range: -4.3517

Max Act: 3.6448. Min Act: -0.0000

Data Index: 345392 (C4 (Web Text))

Max Activating Token Index: 188

Text #8

Max Range: 4.3517. Min Range: -4.3517

Max Act: 3.1600. Min Act: -0.0000

Data Index: 68241 (C4 (Web Text))

Max Activating Token Index: 522

Text #9

Max Range: 4.3517. Min Range: -4.3517

Max Act: 3.5668. Min Act: -0.0000

Data Index: 1359008 (C4 (Web Text))

Max Activating Token Index: 791

Text #10

Max Range: 4.3517. Min Range: -4.3517

Max Act: 3.2518. Min Act: -0.0000

Data Index: 589084 (C4 (Web Text))

Max Activating Token Index: 646

Text #11

Max Range: 4.3517. Min Range: -4.3517

Max Act: 3.3987. Min Act: -0.0000

Data Index: 1084387 (C4 (Web Text))

Max Activating Token Index: 529

Text #12

Max Range: 4.3517. Min Range: -4.3517

Max Act: 3.4067. Min Act: -0.0001

Data Index: 339706 (C4 (Web Text))

Max Activating Token Index: 677

Text #13

Max Range: 4.3517. Min Range: -4.3517

Max Act: 3.5398. Min Act: -0.0000

Data Index: 671451 (C4 (Web Text))

Max Activating Token Index: 325

Text #14

Max Range: 4.3517. Min Range: -4.3517

Max Act: 3.4696. Min Act: -0.0000

Data Index: 320801 (C4 (Web Text))

Max Activating Token Index: 191

Text #15

Max Range: 4.3517. Min Range: -4.3517

Max Act: 3.0417. Min Act: -0.0000

Data Index: 897088 (C4 (Web Text))

Max Activating Token Index: 693

Text #16

Max Range: 4.3517. Min Range: -4.3517

Max Act: 2.6662. Min Act: -0.0000

Data Index: 849939 (C4 (Web Text))

Max Activating Token Index: 319

Text #17

Max Range: 4.3517. Min Range: -4.3517

Max Act: 3.2571. Min Act: -0.0001

Data Index: 160365 (C4 (Web Text))

Max Activating Token Index: 874

Text #18

Max Range: 4.3517. Min Range: -4.3517

Max Act: 3.5231. Min Act: -0.0000

Data Index: 1005304 (C4 (Web Text))

Max Activating Token Index: 1007

Text #19

Max Range: 4.3517. Min Range: -4.3517

Max Act: 3.2330. Min Act: -0.0000

Data Index: 708845 (C4 (Web Text))

Max Activating Token Index: 72