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

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

Neuron 1605 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.2980. Min Range: -1.2980

Max Act: 1.2980. Min Act: -0.0002

Data Index: 813364 (C4 (Web Text))

Max Activating Token Index: 819

Text #1

Max Range: 1.2980. Min Range: -1.2980

Max Act: 1.2052. Min Act: -0.0002

Data Index: 503817 (C4 (Web Text))

Max Activating Token Index: 607

Text #2

Max Range: 1.2980. Min Range: -1.2980

Max Act: 1.1406. Min Act: -0.0002

Data Index: 671244 (C4 (Web Text))

Max Activating Token Index: 813

Text #3

Max Range: 1.2980. Min Range: -1.2980

Max Act: 1.1551. Min Act: -0.0001

Data Index: 201922 (C4 (Web Text))

Max Activating Token Index: 481

Text #4

Max Range: 1.2980. Min Range: -1.2980

Max Act: 1.1149. Min Act: -0.0001

Data Index: 1263314 (C4 (Web Text))

Max Activating Token Index: 379

Text #5

Max Range: 1.2980. Min Range: -1.2980

Max Act: 1.1798. Min Act: -0.0002

Data Index: 1081590 (C4 (Web Text))

Max Activating Token Index: 322

Text #6

Max Range: 1.2980. Min Range: -1.2980

Max Act: 1.1001. Min Act: -0.0001

Data Index: 1147258 (C4 (Web Text))

Max Activating Token Index: 488

Text #7

Max Range: 1.2980. Min Range: -1.2980

Max Act: 1.1592. Min Act: -0.0002

Data Index: 709551 (C4 (Web Text))

Max Activating Token Index: 945

Text #8

Max Range: 1.2980. Min Range: -1.2980

Max Act: 1.1603. Min Act: -0.0001

Data Index: 446445 (C4 (Web Text))

Max Activating Token Index: 860

Text #9

Max Range: 1.2980. Min Range: -1.2980

Max Act: 1.1247. Min Act: -0.0001

Data Index: 192239 (C4 (Web Text))

Max Activating Token Index: 441

Text #10

Max Range: 1.2980. Min Range: -1.2980

Max Act: 1.0736. Min Act: -0.0001

Data Index: 907086 (C4 (Web Text))

Max Activating Token Index: 373

Text #11

Max Range: 1.2980. Min Range: -1.2980

Max Act: 1.0748. Min Act: -0.0002

Data Index: 774706 (C4 (Web Text))

Max Activating Token Index: 294

Text #12

Max Range: 1.2980. Min Range: -1.2980

Max Act: 1.1205. Min Act: -0.0002

Data Index: 839022 (C4 (Web Text))

Max Activating Token Index: 16

Text #13

Max Range: 1.2980. Min Range: -1.2980

Max Act: 1.0755. Min Act: -0.0001

Data Index: 1031540 (C4 (Web Text))

Max Activating Token Index: 810

Text #14

Max Range: 1.2980. Min Range: -1.2980

Max Act: 1.0306. Min Act: -0.0001

Data Index: 342819 (C4 (Web Text))

Max Activating Token Index: 861

Text #15

Max Range: 1.2980. Min Range: -1.2980

Max Act: 1.0653. Min Act: -0.0001

Data Index: 566670 (C4 (Web Text))

Max Activating Token Index: 997

Text #16

Max Range: 1.2980. Min Range: -1.2980

Max Act: 1.0613. Min Act: -0.0001

Data Index: 1068571 (C4 (Web Text))

Max Activating Token Index: 418

Text #17

Max Range: 1.2980. Min Range: -1.2980

Max Act: 1.0599. Min Act: -0.0001

Data Index: 158375 (C4 (Web Text))

Max Activating Token Index: 401

Text #18

Max Range: 1.2980. Min Range: -1.2980

Max Act: 1.0877. Min Act: -0.0002

Data Index: 1241550 (C4 (Web Text))

Max Activating Token Index: 810

Text #19

Max Range: 1.2980. Min Range: -1.2980

Max Act: 1.0750. Min Act: -0.0002

Data Index: 1114708 (C4 (Web Text))

Max Activating Token Index: 383