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

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

Neuron 803 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: 1.9515. Min Range: -1.9515

Max Act: 1.9515. Min Act: -0.0000

Data Index: 1251420 (C4 (Web Text))

Max Activating Token Index: 869

Text #1

Max Range: 1.9515. Min Range: -1.9515

Max Act: 1.9123. Min Act: -0.0000

Data Index: 1263532 (C4 (Web Text))

Max Activating Token Index: 582

Text #2

Max Range: 1.9515. Min Range: -1.9515

Max Act: 1.8683. Min Act: -0.0000

Data Index: 1287427 (C4 (Web Text))

Max Activating Token Index: 619

Text #3

Max Range: 1.9515. Min Range: -1.9515

Max Act: 1.8419. Min Act: -0.0000

Data Index: 1019901 (C4 (Web Text))

Max Activating Token Index: 674

Text #4

Max Range: 1.9515. Min Range: -1.9515

Max Act: 1.8185. Min Act: -0.0000

Data Index: 221172 (C4 (Web Text))

Max Activating Token Index: 429

Text #5

Max Range: 1.9515. Min Range: -1.9515

Max Act: 1.6066. Min Act: -0.0000

Data Index: 839231 (C4 (Web Text))

Max Activating Token Index: 913

Text #6

Max Range: 1.9515. Min Range: -1.9515

Max Act: 1.7672. Min Act: -0.0000

Data Index: 785949 (C4 (Web Text))

Max Activating Token Index: 878

Text #7

Max Range: 1.9515. Min Range: -1.9515

Max Act: 1.6374. Min Act: -0.0000

Data Index: 1116783 (C4 (Web Text))

Max Activating Token Index: 759

Text #8

Max Range: 1.9515. Min Range: -1.9515

Max Act: 1.6195. Min Act: -0.0000

Data Index: 98260 (C4 (Web Text))

Max Activating Token Index: 938

Text #9

Max Range: 1.9515. Min Range: -1.9515

Max Act: 1.6764. Min Act: -0.0000

Data Index: 804655 (C4 (Web Text))

Max Activating Token Index: 164

Text #10

Max Range: 1.9515. Min Range: -1.9515

Max Act: 1.5829. Min Act: -0.0000

Data Index: 288528 (C4 (Web Text))

Max Activating Token Index: 870

Text #11

Max Range: 1.9515. Min Range: -1.9515

Max Act: 1.5807. Min Act: -0.0000

Data Index: 153625 (C4 (Web Text))

Max Activating Token Index: 394

Text #12

Max Range: 1.9515. Min Range: -1.9515

Max Act: 1.5639. Min Act: -0.0000

Data Index: 341815 (C4 (Web Text))

Max Activating Token Index: 670

Text #13

Max Range: 1.9515. Min Range: -1.9515

Max Act: 1.5364. Min Act: -0.0000

Data Index: 426941 (C4 (Web Text))

Max Activating Token Index: 525

Text #14

Max Range: 1.9515. Min Range: -1.9515

Max Act: 1.3415. Min Act: -0.0000

Data Index: 1323776 (C4 (Web Text))

Max Activating Token Index: 193

Text #15

Max Range: 1.9515. Min Range: -1.9515

Max Act: 1.4541. Min Act: -0.0000

Data Index: 822347 (C4 (Web Text))

Max Activating Token Index: 745

Text #16

Max Range: 1.9515. Min Range: -1.9515

Max Act: 1.4482. Min Act: -0.0000

Data Index: 528837 (C4 (Web Text))

Max Activating Token Index: 587

Text #17

Max Range: 1.9515. Min Range: -1.9515

Max Act: 1.4185. Min Act: -0.0000

Data Index: 535130 (C4 (Web Text))

Max Activating Token Index: 695

Text #18

Max Range: 1.9515. Min Range: -1.9515

Max Act: 1.4220. Min Act: -0.0000

Data Index: 323539 (C4 (Web Text))

Max Activating Token Index: 362

Text #19

Max Range: 1.9515. Min Range: -1.9515

Max Act: 1.3349. Min Act: -0.0000

Data Index: 982360 (C4 (Web Text))

Max Activating Token Index: 79