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

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

Neuron 1260 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: 0.3652. Min Range: -0.3652

Max Act: 0.3625. Min Act: -0.0001

Data Index: 427605 (C4 (Web Text))

Max Activating Token Index: 559

Text #1

Max Range: 0.3652. Min Range: -0.3652

Max Act: 0.3517. Min Act: -0.0001

Data Index: 1597394 (Python Code)

Max Activating Token Index: 286

Text #2

Max Range: 0.3652. Min Range: -0.3652

Max Act: 0.3450. Min Act: -0.0001

Data Index: 869536 (C4 (Web Text))

Max Activating Token Index: 689

Text #3

Max Range: 0.3652. Min Range: -0.3652

Max Act: 0.3108. Min Act: -0.0001

Data Index: 554954 (C4 (Web Text))

Max Activating Token Index: 612

Text #4

Max Range: 0.3652. Min Range: -0.3652

Max Act: 0.3652. Min Act: -0.0001

Data Index: 601363 (C4 (Web Text))

Max Activating Token Index: 916

Text #5

Max Range: 0.3652. Min Range: -0.3652

Max Act: 0.3387. Min Act: -0.0001

Data Index: 998850 (C4 (Web Text))

Max Activating Token Index: 483

Text #6

Max Range: 0.3652. Min Range: -0.3652

Max Act: 0.3317. Min Act: -0.0001

Data Index: 46407 (C4 (Web Text))

Max Activating Token Index: 328

Text #7

Max Range: 0.3652. Min Range: -0.3652

Max Act: 0.3140. Min Act: -0.0001

Data Index: 867962 (C4 (Web Text))

Max Activating Token Index: 952

Text #8

Max Range: 0.3652. Min Range: -0.3652

Max Act: 0.3144. Min Act: -0.0001

Data Index: 814889 (C4 (Web Text))

Max Activating Token Index: 415

Text #9

Max Range: 0.3652. Min Range: -0.3652

Max Act: 0.3184. Min Act: -0.0001

Data Index: 734676 (C4 (Web Text))

Max Activating Token Index: 706

Text #10

Max Range: 0.3652. Min Range: -0.3652

Max Act: 0.3034. Min Act: -0.0001

Data Index: 406200 (C4 (Web Text))

Max Activating Token Index: 588

Text #11

Max Range: 0.3652. Min Range: -0.3652

Max Act: 0.3194. Min Act: -0.0001

Data Index: 14579 (C4 (Web Text))

Max Activating Token Index: 208

Text #12

Max Range: 0.3652. Min Range: -0.3652

Max Act: 0.2620. Min Act: -0.0001

Data Index: 1085306 (C4 (Web Text))

Max Activating Token Index: 601

Text #13

Max Range: 0.3652. Min Range: -0.3652

Max Act: 0.2934. Min Act: -0.0001

Data Index: 541918 (C4 (Web Text))

Max Activating Token Index: 867

Text #14

Max Range: 0.3652. Min Range: -0.3652

Max Act: 0.3132. Min Act: -0.0001

Data Index: 1586377 (Python Code)

Max Activating Token Index: 108

Text #15

Max Range: 0.3652. Min Range: -0.3652

Max Act: 0.2933. Min Act: -0.0001

Data Index: 813447 (C4 (Web Text))

Max Activating Token Index: 653

Text #16

Max Range: 0.3652. Min Range: -0.3652

Max Act: 0.2843. Min Act: -0.0001

Data Index: 510688 (C4 (Web Text))

Max Activating Token Index: 450

Text #17

Max Range: 0.3652. Min Range: -0.3652

Max Act: 0.3065. Min Act: -0.0001

Data Index: 12963 (C4 (Web Text))

Max Activating Token Index: 636

Text #18

Max Range: 0.3652. Min Range: -0.3652

Max Act: 0.2606. Min Act: -0.0001

Data Index: 153204 (C4 (Web Text))

Max Activating Token Index: 566

Text #19

Max Range: 0.3652. Min Range: -0.3652

Max Act: 0.2702. Min Act: -0.0001

Data Index: 127355 (C4 (Web Text))

Max Activating Token Index: 864