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

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

Neuron 2041 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: 0.0758. Min Range: -0.0758

Max Act: 0.0758. Min Act: -0.0001

Data Index: 1097874 (C4 (Web Text))

Max Activating Token Index: 861

Text #1

Max Range: 0.0758. Min Range: -0.0758

Max Act: 0.0736. Min Act: -0.0001

Data Index: 1183003 (C4 (Web Text))

Max Activating Token Index: 28

Text #2

Max Range: 0.0758. Min Range: -0.0758

Max Act: 0.0678. Min Act: -0.0001

Data Index: 893888 (C4 (Web Text))

Max Activating Token Index: 725

Text #3

Max Range: 0.0758. Min Range: -0.0758

Max Act: 0.0687. Min Act: -0.0001

Data Index: 773969 (C4 (Web Text))

Max Activating Token Index: 681

Text #4

Max Range: 0.0758. Min Range: -0.0758

Max Act: 0.0631. Min Act: -0.0001

Data Index: 922353 (C4 (Web Text))

Max Activating Token Index: 150

Text #5

Max Range: 0.0758. Min Range: -0.0758

Max Act: 0.0670. Min Act: -0.0001

Data Index: 487963 (C4 (Web Text))

Max Activating Token Index: 756

Text #6

Max Range: 0.0758. Min Range: -0.0758

Max Act: 0.0644. Min Act: -0.0002

Data Index: 12520 (C4 (Web Text))

Max Activating Token Index: 178

Text #7

Max Range: 0.0758. Min Range: -0.0758

Max Act: 0.0597. Min Act: -0.0001

Data Index: 511618 (C4 (Web Text))

Max Activating Token Index: 889

Text #8

Max Range: 0.0758. Min Range: -0.0758

Max Act: 0.0625. Min Act: -0.0001

Data Index: 1056577 (C4 (Web Text))

Max Activating Token Index: 189

Text #9

Max Range: 0.0758. Min Range: -0.0758

Max Act: 0.0584. Min Act: -0.0001

Data Index: 11245 (C4 (Web Text))

Max Activating Token Index: 784

Text #10

Max Range: 0.0758. Min Range: -0.0758

Max Act: 0.0599. Min Act: -0.0001

Data Index: 1334713 (C4 (Web Text))

Max Activating Token Index: 870

Text #11

Max Range: 0.0758. Min Range: -0.0758

Max Act: 0.0620. Min Act: -0.0002

Data Index: 1354653 (C4 (Web Text))

Max Activating Token Index: 242

Text #12

Max Range: 0.0758. Min Range: -0.0758

Max Act: 0.0560. Min Act: -0.0002

Data Index: 387423 (C4 (Web Text))

Max Activating Token Index: 357

Text #13

Max Range: 0.0758. Min Range: -0.0758

Max Act: 0.0599. Min Act: -0.0002

Data Index: 66648 (C4 (Web Text))

Max Activating Token Index: 950

Text #14

Max Range: 0.0758. Min Range: -0.0758

Max Act: 0.0541. Min Act: -0.0002

Data Index: 745477 (C4 (Web Text))

Max Activating Token Index: 709

Text #15

Max Range: 0.0758. Min Range: -0.0758

Max Act: 0.0586. Min Act: -0.0001

Data Index: 1137398 (C4 (Web Text))

Max Activating Token Index: 676

Text #16

Max Range: 0.0758. Min Range: -0.0758

Max Act: 0.0557. Min Act: -0.0002

Data Index: 531436 (C4 (Web Text))

Max Activating Token Index: 333

Text #17

Max Range: 0.0758. Min Range: -0.0758

Max Act: 0.0612. Min Act: -0.0002

Data Index: 736221 (C4 (Web Text))

Max Activating Token Index: 846

Text #18

Max Range: 0.0758. Min Range: -0.0758

Max Act: 0.0552. Min Act: -0.0002

Data Index: 537783 (C4 (Web Text))

Max Activating Token Index: 552

Text #19

Max Range: 0.0758. Min Range: -0.0758

Max Act: 0.0573. Min Act: -0.0002

Data Index: 738740 (C4 (Web Text))

Max Activating Token Index: 468