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

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

Neuron 4051 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1685. Min Range: -0.1685

Max Act: 0.1685. Min Act: -0.0001

Data Index: 470888 (C4 (Web Text))

Max Activating Token Index: 695

Text #1

Max Range: 0.1685. Min Range: -0.1685

Max Act: 0.1545. Min Act: -0.0001

Data Index: 352597 (C4 (Web Text))

Max Activating Token Index: 260

Text #2

Max Range: 0.1685. Min Range: -0.1685

Max Act: 0.1463. Min Act: -0.0001

Data Index: 1254604 (C4 (Web Text))

Max Activating Token Index: 388

Text #3

Max Range: 0.1685. Min Range: -0.1685

Max Act: 0.1520. Min Act: -0.0001

Data Index: 38019 (C4 (Web Text))

Max Activating Token Index: 782

Text #4

Max Range: 0.1685. Min Range: -0.1685

Max Act: 0.1354. Min Act: -0.0001

Data Index: 391176 (C4 (Web Text))

Max Activating Token Index: 374

Text #5

Max Range: 0.1685. Min Range: -0.1685

Max Act: 0.1327. Min Act: -0.0001

Data Index: 308948 (C4 (Web Text))

Max Activating Token Index: 307

Text #6

Max Range: 0.1685. Min Range: -0.1685

Max Act: 0.1263. Min Act: -0.0001

Data Index: 290826 (C4 (Web Text))

Max Activating Token Index: 107

Text #7

Max Range: 0.1685. Min Range: -0.1685

Max Act: 0.1355. Min Act: -0.0001

Data Index: 503029 (C4 (Web Text))

Max Activating Token Index: 273

Text #8

Max Range: 0.1685. Min Range: -0.1685

Max Act: 0.1102. Min Act: -0.0001

Data Index: 1090155 (C4 (Web Text))

Max Activating Token Index: 549

Text #9

Max Range: 0.1685. Min Range: -0.1685

Max Act: 0.1335. Min Act: -0.0001

Data Index: 247647 (C4 (Web Text))

Max Activating Token Index: 823

Text #10

Max Range: 0.1685. Min Range: -0.1685

Max Act: 0.1244. Min Act: -0.0001

Data Index: 679309 (C4 (Web Text))

Max Activating Token Index: 503

Text #11

Max Range: 0.1685. Min Range: -0.1685

Max Act: 0.1361. Min Act: -0.0001

Data Index: 100546 (C4 (Web Text))

Max Activating Token Index: 655

Text #12

Max Range: 0.1685. Min Range: -0.1685

Max Act: 0.1229. Min Act: -0.0001

Data Index: 55648 (C4 (Web Text))

Max Activating Token Index: 691

Text #13

Max Range: 0.1685. Min Range: -0.1685

Max Act: 0.1222. Min Act: -0.0001

Data Index: 1285884 (C4 (Web Text))

Max Activating Token Index: 85

Text #14

Max Range: 0.1685. Min Range: -0.1685

Max Act: 0.1200. Min Act: -0.0001

Data Index: 268417 (C4 (Web Text))

Max Activating Token Index: 638

Text #15

Max Range: 0.1685. Min Range: -0.1685

Max Act: 0.1249. Min Act: -0.0001

Data Index: 273081 (C4 (Web Text))

Max Activating Token Index: 530

Text #16

Max Range: 0.1685. Min Range: -0.1685

Max Act: 0.1236. Min Act: -0.0001

Data Index: 994216 (C4 (Web Text))

Max Activating Token Index: 500

Text #17

Max Range: 0.1685. Min Range: -0.1685

Max Act: 0.1234. Min Act: -0.0001

Data Index: 207035 (C4 (Web Text))

Max Activating Token Index: 682

Text #18

Max Range: 0.1685. Min Range: -0.1685

Max Act: 0.1234. Min Act: -0.0001

Data Index: 1153090 (C4 (Web Text))

Max Activating Token Index: 461

Text #19

Max Range: 0.1685. Min Range: -0.1685

Max Act: 0.1226. Min Act: -0.0001

Data Index: 1005181 (C4 (Web Text))

Max Activating Token Index: 841