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

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

Neuron 4381 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: 3.4378. Min Range: -3.4378

Max Act: 3.4378. Min Act: -0.0000

Data Index: 508513 (C4 (Web Text))

Max Activating Token Index: 728

Text #1

Max Range: 3.4378. Min Range: -3.4378

Max Act: 2.9409. Min Act: -0.0000

Data Index: 1638703 (Python Code)

Max Activating Token Index: 891

Text #2

Max Range: 3.4378. Min Range: -3.4378

Max Act: 2.9386. Min Act: -0.0000

Data Index: 424031 (C4 (Web Text))

Max Activating Token Index: 491

Text #3

Max Range: 3.4378. Min Range: -3.4378

Max Act: 2.8867. Min Act: -0.0000

Data Index: 1233965 (C4 (Web Text))

Max Activating Token Index: 770

Text #4

Max Range: 3.4378. Min Range: -3.4378

Max Act: 2.9846. Min Act: -0.0000

Data Index: 720885 (C4 (Web Text))

Max Activating Token Index: 795

Text #5

Max Range: 3.4378. Min Range: -3.4378

Max Act: 2.5337. Min Act: -0.0000

Data Index: 81267 (C4 (Web Text))

Max Activating Token Index: 904

Text #6

Max Range: 3.4378. Min Range: -3.4378

Max Act: 2.8129. Min Act: -0.0000

Data Index: 1370349 (Python Code)

Max Activating Token Index: 232

Text #7

Max Range: 3.4378. Min Range: -3.4378

Max Act: 2.4859. Min Act: -0.0000

Data Index: 615365 (C4 (Web Text))

Max Activating Token Index: 125

Text #8

Max Range: 3.4378. Min Range: -3.4378

Max Act: 2.7189. Min Act: -0.0000

Data Index: 791022 (C4 (Web Text))

Max Activating Token Index: 470

Text #9

Max Range: 3.4378. Min Range: -3.4378

Max Act: 2.7114. Min Act: -0.0000

Data Index: 943123 (C4 (Web Text))

Max Activating Token Index: 770

Text #10

Max Range: 3.4378. Min Range: -3.4378

Max Act: 2.5584. Min Act: -0.0000

Data Index: 38460 (C4 (Web Text))

Max Activating Token Index: 695

Text #11

Max Range: 3.4378. Min Range: -3.4378

Max Act: 2.7056. Min Act: -0.0000

Data Index: 1245263 (C4 (Web Text))

Max Activating Token Index: 949

Text #12

Max Range: 3.4378. Min Range: -3.4378

Max Act: 2.8211. Min Act: -0.0000

Data Index: 1386632 (Python Code)

Max Activating Token Index: 994

Text #13

Max Range: 3.4378. Min Range: -3.4378

Max Act: 2.4903. Min Act: -0.0000

Data Index: 13130 (C4 (Web Text))

Max Activating Token Index: 176

Text #14

Max Range: 3.4378. Min Range: -3.4378

Max Act: 2.5325. Min Act: -0.0000

Data Index: 210651 (C4 (Web Text))

Max Activating Token Index: 383

Text #15

Max Range: 3.4378. Min Range: -3.4378

Max Act: 2.6475. Min Act: -0.0000

Data Index: 360192 (C4 (Web Text))

Max Activating Token Index: 807

Text #16

Max Range: 3.4378. Min Range: -3.4378

Max Act: 2.9061. Min Act: -0.0000

Data Index: 486493 (C4 (Web Text))

Max Activating Token Index: 708

Text #17

Max Range: 3.4378. Min Range: -3.4378

Max Act: 2.6393. Min Act: -0.0000

Data Index: 223789 (C4 (Web Text))

Max Activating Token Index: 516

Text #18

Max Range: 3.4378. Min Range: -3.4378

Max Act: 2.5982. Min Act: -0.0000

Data Index: 1028272 (C4 (Web Text))

Max Activating Token Index: 512

Text #19

Max Range: 3.4378. Min Range: -3.4378

Max Act: 2.4456. Min Act: -0.0000

Data Index: 954697 (C4 (Web Text))

Max Activating Token Index: 406