Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 6005 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.6595. Min Range: -0.6595

Max Act: 0.6595. Min Act: -0.0000

Data Index: 1141243 (C4 (Web Text))

Max Activating Token Index: 91

Text #1

Max Range: 0.6595. Min Range: -0.6595

Max Act: 0.6212. Min Act: -0.0000

Data Index: 616414 (C4 (Web Text))

Max Activating Token Index: 996

Text #2

Max Range: 0.6595. Min Range: -0.6595

Max Act: 0.5699. Min Act: -0.0000

Data Index: 125789 (C4 (Web Text))

Max Activating Token Index: 824

Text #3

Max Range: 0.6595. Min Range: -0.6595

Max Act: 0.6161. Min Act: -0.0000

Data Index: 483358 (C4 (Web Text))

Max Activating Token Index: 829

Text #4

Max Range: 0.6595. Min Range: -0.6595

Max Act: 0.5432. Min Act: -0.0000

Data Index: 227651 (C4 (Web Text))

Max Activating Token Index: 771

Text #5

Max Range: 0.6595. Min Range: -0.6595

Max Act: 0.5079. Min Act: -0.0000

Data Index: 781399 (C4 (Web Text))

Max Activating Token Index: 624

Text #6

Max Range: 0.6595. Min Range: -0.6595

Max Act: 0.4974. Min Act: -0.0000

Data Index: 817250 (C4 (Web Text))

Max Activating Token Index: 622

Text #7

Max Range: 0.6595. Min Range: -0.6595

Max Act: 0.4768. Min Act: -0.0000

Data Index: 139682 (C4 (Web Text))

Max Activating Token Index: 284

Text #8

Max Range: 0.6595. Min Range: -0.6595

Max Act: 0.4617. Min Act: -0.0000

Data Index: 1051233 (C4 (Web Text))

Max Activating Token Index: 684

Text #9

Max Range: 0.6595. Min Range: -0.6595

Max Act: 0.4456. Min Act: -0.0000

Data Index: 686622 (C4 (Web Text))

Max Activating Token Index: 537

Text #10

Max Range: 0.6595. Min Range: -0.6595

Max Act: 0.4427. Min Act: -0.0000

Data Index: 887285 (C4 (Web Text))

Max Activating Token Index: 782

Text #11

Max Range: 0.6595. Min Range: -0.6595

Max Act: 0.4397. Min Act: -0.0000

Data Index: 1029050 (C4 (Web Text))

Max Activating Token Index: 300

Text #12

Max Range: 0.6595. Min Range: -0.6595

Max Act: 0.4738. Min Act: -0.0000

Data Index: 1141671 (C4 (Web Text))

Max Activating Token Index: 984

Text #13

Max Range: 0.6595. Min Range: -0.6595

Max Act: 0.4404. Min Act: -0.0000

Data Index: 680992 (C4 (Web Text))

Max Activating Token Index: 781

Text #14

Max Range: 0.6595. Min Range: -0.6595

Max Act: 0.3964. Min Act: -0.0000

Data Index: 782706 (C4 (Web Text))

Max Activating Token Index: 639

Text #15

Max Range: 0.6595. Min Range: -0.6595

Max Act: 0.4537. Min Act: -0.0000

Data Index: 448626 (C4 (Web Text))

Max Activating Token Index: 969

Text #16

Max Range: 0.6595. Min Range: -0.6595

Max Act: 0.4207. Min Act: -0.0000

Data Index: 1309906 (C4 (Web Text))

Max Activating Token Index: 690

Text #17

Max Range: 0.6595. Min Range: -0.6595

Max Act: 0.4196. Min Act: -0.0000

Data Index: 1295894 (C4 (Web Text))

Max Activating Token Index: 385

Text #18

Max Range: 0.6595. Min Range: -0.6595

Max Act: 0.4304. Min Act: -0.0000

Data Index: 176542 (C4 (Web Text))

Max Activating Token Index: 614

Text #19

Max Range: 0.6595. Min Range: -0.6595

Max Act: 0.4590. Min Act: -0.0000

Data Index: 770267 (C4 (Web Text))

Max Activating Token Index: 440