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

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

Neuron 2973 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: 0.1462. Min Range: -0.1462

Max Act: 0.1462. Min Act: -0.0001

Data Index: 223866 (C4 (Web Text))

Max Activating Token Index: 266

Text #1

Max Range: 0.1462. Min Range: -0.1462

Max Act: 0.1357. Min Act: -0.0001

Data Index: 610301 (C4 (Web Text))

Max Activating Token Index: 509

Text #2

Max Range: 0.1462. Min Range: -0.1462

Max Act: 0.1431. Min Act: -0.0001

Data Index: 749461 (C4 (Web Text))

Max Activating Token Index: 238

Text #3

Max Range: 0.1462. Min Range: -0.1462

Max Act: 0.1329. Min Act: -0.0001

Data Index: 744841 (C4 (Web Text))

Max Activating Token Index: 968

Text #4

Max Range: 0.1462. Min Range: -0.1462

Max Act: 0.1319. Min Act: -0.0001

Data Index: 479016 (C4 (Web Text))

Max Activating Token Index: 760

Text #5

Max Range: 0.1462. Min Range: -0.1462

Max Act: 0.1351. Min Act: -0.0001

Data Index: 633721 (C4 (Web Text))

Max Activating Token Index: 776

Text #6

Max Range: 0.1462. Min Range: -0.1462

Max Act: 0.1253. Min Act: -0.0001

Data Index: 11571 (C4 (Web Text))

Max Activating Token Index: 310

Text #7

Max Range: 0.1462. Min Range: -0.1462

Max Act: 0.1286. Min Act: -0.0001

Data Index: 1320329 (C4 (Web Text))

Max Activating Token Index: 147

Text #8

Max Range: 0.1462. Min Range: -0.1462

Max Act: 0.1291. Min Act: -0.0001

Data Index: 517080 (C4 (Web Text))

Max Activating Token Index: 933

Text #9

Max Range: 0.1462. Min Range: -0.1462

Max Act: 0.1215. Min Act: -0.0001

Data Index: 1211038 (C4 (Web Text))

Max Activating Token Index: 580

Text #10

Max Range: 0.1462. Min Range: -0.1462

Max Act: 0.1270. Min Act: -0.0001

Data Index: 1094605 (C4 (Web Text))

Max Activating Token Index: 840

Text #11

Max Range: 0.1462. Min Range: -0.1462

Max Act: 0.1258. Min Act: -0.0001

Data Index: 1143432 (C4 (Web Text))

Max Activating Token Index: 204

Text #12

Max Range: 0.1462. Min Range: -0.1462

Max Act: 0.1258. Min Act: -0.0001

Data Index: 822304 (C4 (Web Text))

Max Activating Token Index: 157

Text #13

Max Range: 0.1462. Min Range: -0.1462

Max Act: 0.1252. Min Act: -0.0001

Data Index: 904024 (C4 (Web Text))

Max Activating Token Index: 552

Text #14

Max Range: 0.1462. Min Range: -0.1462

Max Act: 0.1172. Min Act: -0.0001

Data Index: 101516 (C4 (Web Text))

Max Activating Token Index: 404

Text #15

Max Range: 0.1462. Min Range: -0.1462

Max Act: 0.1173. Min Act: -0.0000

Data Index: 425897 (C4 (Web Text))

Max Activating Token Index: 450

Text #16

Max Range: 0.1462. Min Range: -0.1462

Max Act: 0.1212. Min Act: -0.0000

Data Index: 348347 (C4 (Web Text))

Max Activating Token Index: 482

Text #17

Max Range: 0.1462. Min Range: -0.1462

Max Act: 0.1212. Min Act: -0.0001

Data Index: 303955 (C4 (Web Text))

Max Activating Token Index: 709

Text #18

Max Range: 0.1462. Min Range: -0.1462

Max Act: 0.1286. Min Act: -0.0001

Data Index: 298900 (C4 (Web Text))

Max Activating Token Index: 291

Text #19

Max Range: 0.1462. Min Range: -0.1462

Max Act: 0.1212. Min Act: -0.0001

Data Index: 71442 (C4 (Web Text))

Max Activating Token Index: 483