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

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

Neuron 2328 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: 0.1564. Min Range: -0.1564

Max Act: 0.1564. Min Act: -0.0001

Data Index: 1155029 (C4 (Web Text))

Max Activating Token Index: 204

Text #1

Max Range: 0.1564. Min Range: -0.1564

Max Act: 0.1544. Min Act: -0.0000

Data Index: 1138814 (C4 (Web Text))

Max Activating Token Index: 903

Text #2

Max Range: 0.1564. Min Range: -0.1564

Max Act: 0.1521. Min Act: -0.0001

Data Index: 1293561 (C4 (Web Text))

Max Activating Token Index: 275

Text #3

Max Range: 0.1564. Min Range: -0.1564

Max Act: 0.1398. Min Act: -0.0001

Data Index: 1343304 (C4 (Web Text))

Max Activating Token Index: 368

Text #4

Max Range: 0.1564. Min Range: -0.1564

Max Act: 0.1371. Min Act: -0.0001

Data Index: 557614 (C4 (Web Text))

Max Activating Token Index: 237

Text #5

Max Range: 0.1564. Min Range: -0.1564

Max Act: 0.1368. Min Act: -0.0000

Data Index: 1205028 (C4 (Web Text))

Max Activating Token Index: 295

Text #6

Max Range: 0.1564. Min Range: -0.1564

Max Act: 0.1277. Min Act: -0.0001

Data Index: 127650 (C4 (Web Text))

Max Activating Token Index: 234

Text #7

Max Range: 0.1564. Min Range: -0.1564

Max Act: 0.1319. Min Act: -0.0001

Data Index: 256509 (C4 (Web Text))

Max Activating Token Index: 458

Text #8

Max Range: 0.1564. Min Range: -0.1564

Max Act: 0.1312. Min Act: -0.0001

Data Index: 313378 (C4 (Web Text))

Max Activating Token Index: 124

Text #9

Max Range: 0.1564. Min Range: -0.1564

Max Act: 0.1313. Min Act: -0.0001

Data Index: 874309 (C4 (Web Text))

Max Activating Token Index: 510

Text #10

Max Range: 0.1564. Min Range: -0.1564

Max Act: 0.1236. Min Act: -0.0001

Data Index: 922379 (C4 (Web Text))

Max Activating Token Index: 514

Text #11

Max Range: 0.1564. Min Range: -0.1564

Max Act: 0.1308. Min Act: -0.0001

Data Index: 1307917 (C4 (Web Text))

Max Activating Token Index: 371

Text #12

Max Range: 0.1564. Min Range: -0.1564

Max Act: 0.1244. Min Act: -0.0001

Data Index: 149807 (C4 (Web Text))

Max Activating Token Index: 726

Text #13

Max Range: 0.1564. Min Range: -0.1564

Max Act: 0.1199. Min Act: -0.0001

Data Index: 1008440 (C4 (Web Text))

Max Activating Token Index: 405

Text #14

Max Range: 0.1564. Min Range: -0.1564

Max Act: 0.1241. Min Act: -0.0001

Data Index: 902621 (C4 (Web Text))

Max Activating Token Index: 127

Text #15

Max Range: 0.1564. Min Range: -0.1564

Max Act: 0.1283. Min Act: -0.0001

Data Index: 753250 (C4 (Web Text))

Max Activating Token Index: 802

Text #16

Max Range: 0.1564. Min Range: -0.1564

Max Act: 0.1277. Min Act: -0.0001

Data Index: 953984 (C4 (Web Text))

Max Activating Token Index: 774

Text #17

Max Range: 0.1564. Min Range: -0.1564

Max Act: 0.1253. Min Act: -0.0001

Data Index: 1258306 (C4 (Web Text))

Max Activating Token Index: 274

Text #18

Max Range: 0.1564. Min Range: -0.1564

Max Act: 0.1147. Min Act: -0.0001

Data Index: 967815 (C4 (Web Text))

Max Activating Token Index: 850

Text #19

Max Range: 0.1564. Min Range: -0.1564

Max Act: 0.1261. Min Act: -0.0001

Data Index: 112616 (C4 (Web Text))

Max Activating Token Index: 718