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

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

Neuron 1937 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.1764. Min Range: -0.1764

Max Act: 0.1611. Min Act: -0.0001

Data Index: 1169513 (C4 (Web Text))

Max Activating Token Index: 555

Text #1

Max Range: 0.1764. Min Range: -0.1764

Max Act: 0.1764. Min Act: -0.0001

Data Index: 1212185 (C4 (Web Text))

Max Activating Token Index: 303

Text #2

Max Range: 0.1764. Min Range: -0.1764

Max Act: 0.1607. Min Act: -0.0001

Data Index: 167976 (C4 (Web Text))

Max Activating Token Index: 234

Text #3

Max Range: 0.1764. Min Range: -0.1764

Max Act: 0.1478. Min Act: -0.0001

Data Index: 138695 (C4 (Web Text))

Max Activating Token Index: 614

Text #4

Max Range: 0.1764. Min Range: -0.1764

Max Act: 0.1368. Min Act: -0.0001

Data Index: 96427 (C4 (Web Text))

Max Activating Token Index: 317

Text #5

Max Range: 0.1764. Min Range: -0.1764

Max Act: 0.1344. Min Act: -0.0001

Data Index: 79245 (C4 (Web Text))

Max Activating Token Index: 313

Text #6

Max Range: 0.1764. Min Range: -0.1764

Max Act: 0.1284. Min Act: -0.0001

Data Index: 47612 (C4 (Web Text))

Max Activating Token Index: 83

Text #7

Max Range: 0.1764. Min Range: -0.1764

Max Act: 0.1255. Min Act: -0.0001

Data Index: 414139 (C4 (Web Text))

Max Activating Token Index: 315

Text #8

Max Range: 0.1764. Min Range: -0.1764

Max Act: 0.1217. Min Act: -0.0001

Data Index: 589397 (C4 (Web Text))

Max Activating Token Index: 379

Text #9

Max Range: 0.1764. Min Range: -0.1764

Max Act: 0.1201. Min Act: -0.0000

Data Index: 918502 (C4 (Web Text))

Max Activating Token Index: 859

Text #10

Max Range: 0.1764. Min Range: -0.1764

Max Act: 0.1201. Min Act: -0.0001

Data Index: 1140562 (C4 (Web Text))

Max Activating Token Index: 111

Text #11

Max Range: 0.1764. Min Range: -0.1764

Max Act: 0.1237. Min Act: -0.0001

Data Index: 794172 (C4 (Web Text))

Max Activating Token Index: 650

Text #12

Max Range: 0.1764. Min Range: -0.1764

Max Act: 0.1286. Min Act: -0.0000

Data Index: 418850 (C4 (Web Text))

Max Activating Token Index: 645

Text #13

Max Range: 0.1764. Min Range: -0.1764

Max Act: 0.1152. Min Act: -0.0001

Data Index: 861068 (C4 (Web Text))

Max Activating Token Index: 780

Text #14

Max Range: 0.1764. Min Range: -0.1764

Max Act: 0.1159. Min Act: -0.0001

Data Index: 859126 (C4 (Web Text))

Max Activating Token Index: 399

Text #15

Max Range: 0.1764. Min Range: -0.1764

Max Act: 0.1298. Min Act: -0.0000

Data Index: 153947 (C4 (Web Text))

Max Activating Token Index: 919

Text #16

Max Range: 0.1764. Min Range: -0.1764

Max Act: 0.1287. Min Act: -0.0001

Data Index: 821389 (C4 (Web Text))

Max Activating Token Index: 168

Text #17

Max Range: 0.1764. Min Range: -0.1764

Max Act: 0.1169. Min Act: -0.0001

Data Index: 1260784 (C4 (Web Text))

Max Activating Token Index: 493

Text #18

Max Range: 0.1764. Min Range: -0.1764

Max Act: 0.1182. Min Act: -0.0000

Data Index: 407763 (C4 (Web Text))

Max Activating Token Index: 789

Text #19

Max Range: 0.1764. Min Range: -0.1764

Max Act: 0.1211. Min Act: -0.0001

Data Index: 673483 (C4 (Web Text))

Max Activating Token Index: 355