Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 1780 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.5402. Min Range: -0.5402

Max Act: 0.5402. Min Act: -0.0001

Data Index: 1195013 (C4 (Web Text))

Max Activating Token Index: 104

Text #1

Max Range: 0.5402. Min Range: -0.5402

Max Act: 0.4579. Min Act: -0.0001

Data Index: 1126818 (C4 (Web Text))

Max Activating Token Index: 219

Text #2

Max Range: 0.5402. Min Range: -0.5402

Max Act: 0.4784. Min Act: -0.0001

Data Index: 25645 (C4 (Web Text))

Max Activating Token Index: 296

Text #3

Max Range: 0.5402. Min Range: -0.5402

Max Act: 0.4521. Min Act: -0.0001

Data Index: 329494 (C4 (Web Text))

Max Activating Token Index: 118

Text #4

Max Range: 0.5402. Min Range: -0.5402

Max Act: 0.4341. Min Act: -0.0001

Data Index: 251085 (C4 (Web Text))

Max Activating Token Index: 683

Text #5

Max Range: 0.5402. Min Range: -0.5402

Max Act: 0.4475. Min Act: -0.0001

Data Index: 434867 (C4 (Web Text))

Max Activating Token Index: 96

Text #6

Max Range: 0.5402. Min Range: -0.5402

Max Act: 0.4346. Min Act: -0.0001

Data Index: 917447 (C4 (Web Text))

Max Activating Token Index: 682

Text #7

Max Range: 0.5402. Min Range: -0.5402

Max Act: 0.4298. Min Act: -0.0001

Data Index: 1117744 (C4 (Web Text))

Max Activating Token Index: 291

Text #8

Max Range: 0.5402. Min Range: -0.5402

Max Act: 0.4557. Min Act: -0.0000

Data Index: 1050714 (C4 (Web Text))

Max Activating Token Index: 482

Text #9

Max Range: 0.5402. Min Range: -0.5402

Max Act: 0.4564. Min Act: -0.0001

Data Index: 1176451 (C4 (Web Text))

Max Activating Token Index: 183

Text #10

Max Range: 0.5402. Min Range: -0.5402

Max Act: 0.4418. Min Act: -0.0001

Data Index: 35719 (C4 (Web Text))

Max Activating Token Index: 541

Text #11

Max Range: 0.5402. Min Range: -0.5402

Max Act: 0.4732. Min Act: -0.0001

Data Index: 1605068 (Python Code)

Max Activating Token Index: 992

Text #12

Max Range: 0.5402. Min Range: -0.5402

Max Act: 0.4417. Min Act: -0.0000

Data Index: 809429 (C4 (Web Text))

Max Activating Token Index: 555

Text #13

Max Range: 0.5402. Min Range: -0.5402

Max Act: 0.4403. Min Act: -0.0001

Data Index: 942872 (C4 (Web Text))

Max Activating Token Index: 889

Text #14

Max Range: 0.5402. Min Range: -0.5402

Max Act: 0.4259. Min Act: -0.0001

Data Index: 1217911 (C4 (Web Text))

Max Activating Token Index: 939

Text #15

Max Range: 0.5402. Min Range: -0.5402

Max Act: 0.4384. Min Act: -0.0001

Data Index: 510976 (C4 (Web Text))

Max Activating Token Index: 883

Text #16

Max Range: 0.5402. Min Range: -0.5402

Max Act: 0.4326. Min Act: -0.0001

Data Index: 1183008 (C4 (Web Text))

Max Activating Token Index: 1014

Text #17

Max Range: 0.5402. Min Range: -0.5402

Max Act: 0.4329. Min Act: -0.0001

Data Index: 225598 (C4 (Web Text))

Max Activating Token Index: 416

Text #18

Max Range: 0.5402. Min Range: -0.5402

Max Act: 0.4463. Min Act: -0.0001

Data Index: 1019553 (C4 (Web Text))

Max Activating Token Index: 427

Text #19

Max Range: 0.5402. Min Range: -0.5402

Max Act: 0.4216. Min Act: -0.0001

Data Index: 498395 (C4 (Web Text))

Max Activating Token Index: 394