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

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

Neuron 3606 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.1096. Min Range: -1.1096

Max Act: 1.0586. Min Act: -0.0001

Data Index: 489597 (C4 (Web Text))

Max Activating Token Index: 337

Text #1

Max Range: 1.1096. Min Range: -1.1096

Max Act: 1.1030. Min Act: -0.0001

Data Index: 388377 (C4 (Web Text))

Max Activating Token Index: 412

Text #2

Max Range: 1.1096. Min Range: -1.1096

Max Act: 0.9172. Min Act: -0.0001

Data Index: 332665 (C4 (Web Text))

Max Activating Token Index: 527

Text #3

Max Range: 1.1096. Min Range: -1.1096

Max Act: 0.9250. Min Act: -0.0001

Data Index: 586293 (C4 (Web Text))

Max Activating Token Index: 392

Text #4

Max Range: 1.1096. Min Range: -1.1096

Max Act: 1.1096. Min Act: -0.0001

Data Index: 583078 (C4 (Web Text))

Max Activating Token Index: 420

Text #5

Max Range: 1.1096. Min Range: -1.1096

Max Act: 1.0724. Min Act: -0.0001

Data Index: 815773 (C4 (Web Text))

Max Activating Token Index: 574

Text #6

Max Range: 1.1096. Min Range: -1.1096

Max Act: 0.9908. Min Act: -0.0001

Data Index: 443794 (C4 (Web Text))

Max Activating Token Index: 483

Text #7

Max Range: 1.1096. Min Range: -1.1096

Max Act: 0.9127. Min Act: -0.0001

Data Index: 99125 (C4 (Web Text))

Max Activating Token Index: 493

Text #8

Max Range: 1.1096. Min Range: -1.1096

Max Act: 0.9817. Min Act: -0.0001

Data Index: 78255 (C4 (Web Text))

Max Activating Token Index: 413

Text #9

Max Range: 1.1096. Min Range: -1.1096

Max Act: 0.8946. Min Act: -0.0001

Data Index: 795251 (C4 (Web Text))

Max Activating Token Index: 607

Text #10

Max Range: 1.1096. Min Range: -1.1096

Max Act: 0.9875. Min Act: -0.0001

Data Index: 678730 (C4 (Web Text))

Max Activating Token Index: 547

Text #11

Max Range: 1.1096. Min Range: -1.1096

Max Act: 0.8639. Min Act: -0.0001

Data Index: 1047634 (C4 (Web Text))

Max Activating Token Index: 535

Text #12

Max Range: 1.1096. Min Range: -1.1096

Max Act: 0.9578. Min Act: -0.0001

Data Index: 600671 (C4 (Web Text))

Max Activating Token Index: 782

Text #13

Max Range: 1.1096. Min Range: -1.1096

Max Act: 0.8646. Min Act: -0.0001

Data Index: 1113028 (C4 (Web Text))

Max Activating Token Index: 466

Text #14

Max Range: 1.1096. Min Range: -1.1096

Max Act: 0.8737. Min Act: -0.0000

Data Index: 509989 (C4 (Web Text))

Max Activating Token Index: 197

Text #15

Max Range: 1.1096. Min Range: -1.1096

Max Act: 0.9197. Min Act: -0.0001

Data Index: 697025 (C4 (Web Text))

Max Activating Token Index: 522

Text #16

Max Range: 1.1096. Min Range: -1.1096

Max Act: 0.8914. Min Act: -0.0001

Data Index: 877957 (C4 (Web Text))

Max Activating Token Index: 353

Text #17

Max Range: 1.1096. Min Range: -1.1096

Max Act: 0.8635. Min Act: -0.0001

Data Index: 1250724 (C4 (Web Text))

Max Activating Token Index: 945

Text #18

Max Range: 1.1096. Min Range: -1.1096

Max Act: 0.8136. Min Act: -0.0001

Data Index: 410551 (C4 (Web Text))

Max Activating Token Index: 212

Text #19

Max Range: 1.1096. Min Range: -1.1096

Max Act: 0.8441. Min Act: -0.0001

Data Index: 840050 (C4 (Web Text))

Max Activating Token Index: 841