Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 2675 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.1797. Min Range: -0.1797

Max Act: 0.1797. Min Act: -0.0001

Data Index: 670738 (C4 (Web Text))

Max Activating Token Index: 895

Text #1

Max Range: 0.1797. Min Range: -0.1797

Max Act: 0.1607. Min Act: -0.0001

Data Index: 21975 (C4 (Web Text))

Max Activating Token Index: 58

Text #2

Max Range: 0.1797. Min Range: -0.1797

Max Act: 0.1609. Min Act: -0.0001

Data Index: 900133 (C4 (Web Text))

Max Activating Token Index: 32

Text #3

Max Range: 0.1797. Min Range: -0.1797

Max Act: 0.1439. Min Act: -0.0001

Data Index: 590847 (C4 (Web Text))

Max Activating Token Index: 193

Text #4

Max Range: 0.1797. Min Range: -0.1797

Max Act: 0.1524. Min Act: -0.0001

Data Index: 1329937 (C4 (Web Text))

Max Activating Token Index: 492

Text #5

Max Range: 0.1797. Min Range: -0.1797

Max Act: 0.1438. Min Act: -0.0000

Data Index: 1106075 (C4 (Web Text))

Max Activating Token Index: 879

Text #6

Max Range: 0.1797. Min Range: -0.1797

Max Act: 0.1389. Min Act: -0.0001

Data Index: 1150056 (C4 (Web Text))

Max Activating Token Index: 288

Text #7

Max Range: 0.1797. Min Range: -0.1797

Max Act: 0.1372. Min Act: -0.0001

Data Index: 949757 (C4 (Web Text))

Max Activating Token Index: 896

Text #8

Max Range: 0.1797. Min Range: -0.1797

Max Act: 0.1344. Min Act: -0.0001

Data Index: 562532 (C4 (Web Text))

Max Activating Token Index: 75

Text #9

Max Range: 0.1797. Min Range: -0.1797

Max Act: 0.1264. Min Act: -0.0001

Data Index: 779430 (C4 (Web Text))

Max Activating Token Index: 200

Text #10

Max Range: 0.1797. Min Range: -0.1797

Max Act: 0.1300. Min Act: -0.0001

Data Index: 167607 (C4 (Web Text))

Max Activating Token Index: 147

Text #11

Max Range: 0.1797. Min Range: -0.1797

Max Act: 0.1299. Min Act: -0.0001

Data Index: 1008289 (C4 (Web Text))

Max Activating Token Index: 961

Text #12

Max Range: 0.1797. Min Range: -0.1797

Max Act: 0.1271. Min Act: -0.0001

Data Index: 629799 (C4 (Web Text))

Max Activating Token Index: 492

Text #13

Max Range: 0.1797. Min Range: -0.1797

Max Act: 0.1248. Min Act: 0.0001

Data Index: 1334766 (C4 (Web Text))

Max Activating Token Index: 155

Text #14

Max Range: 0.1797. Min Range: -0.1797

Max Act: 0.1294. Min Act: -0.0000

Data Index: 810766 (C4 (Web Text))

Max Activating Token Index: 787

Text #15

Max Range: 0.1797. Min Range: -0.1797

Max Act: 0.1200. Min Act: -0.0000

Data Index: 785605 (C4 (Web Text))

Max Activating Token Index: 465

Text #16

Max Range: 0.1797. Min Range: -0.1797

Max Act: 0.1208. Min Act: -0.0001

Data Index: 6979 (C4 (Web Text))

Max Activating Token Index: 987

Text #17

Max Range: 0.1797. Min Range: -0.1797

Max Act: 0.1234. Min Act: -0.0001

Data Index: 891309 (C4 (Web Text))

Max Activating Token Index: 662

Text #18

Max Range: 0.1797. Min Range: -0.1797

Max Act: 0.1246. Min Act: -0.0001

Data Index: 484443 (C4 (Web Text))

Max Activating Token Index: 316

Text #19

Max Range: 0.1797. Min Range: -0.1797

Max Act: 0.1237. Min Act: -0.0000

Data Index: 57066 (C4 (Web Text))

Max Activating Token Index: 782