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

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

Neuron 3841 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0739. Min Range: -1.0739

Max Act: 1.0531. Min Act: -0.0001

Data Index: 44037 (C4 (Web Text))

Max Activating Token Index: 273

Text #1

Max Range: 1.0739. Min Range: -1.0739

Max Act: 1.0739. Min Act: -0.0001

Data Index: 1204526 (C4 (Web Text))

Max Activating Token Index: 538

Text #2

Max Range: 1.0739. Min Range: -1.0739

Max Act: 1.0269. Min Act: -0.0001

Data Index: 953239 (C4 (Web Text))

Max Activating Token Index: 387

Text #3

Max Range: 1.0739. Min Range: -1.0739

Max Act: 1.0124. Min Act: -0.0001

Data Index: 349547 (C4 (Web Text))

Max Activating Token Index: 643

Text #4

Max Range: 1.0739. Min Range: -1.0739

Max Act: 0.9816. Min Act: -0.0001

Data Index: 555648 (C4 (Web Text))

Max Activating Token Index: 986

Text #5

Max Range: 1.0739. Min Range: -1.0739

Max Act: 1.0317. Min Act: -0.0001

Data Index: 609494 (C4 (Web Text))

Max Activating Token Index: 384

Text #6

Max Range: 1.0739. Min Range: -1.0739

Max Act: 0.9671. Min Act: -0.0001

Data Index: 1250963 (C4 (Web Text))

Max Activating Token Index: 365

Text #7

Max Range: 1.0739. Min Range: -1.0739

Max Act: 1.0293. Min Act: -0.0001

Data Index: 726607 (C4 (Web Text))

Max Activating Token Index: 591

Text #8

Max Range: 1.0739. Min Range: -1.0739

Max Act: 0.9573. Min Act: -0.0001

Data Index: 331754 (C4 (Web Text))

Max Activating Token Index: 90

Text #9

Max Range: 1.0739. Min Range: -1.0739

Max Act: 0.9603. Min Act: -0.0001

Data Index: 772608 (C4 (Web Text))

Max Activating Token Index: 604

Text #10

Max Range: 1.0739. Min Range: -1.0739

Max Act: 0.9830. Min Act: -0.0001

Data Index: 604196 (C4 (Web Text))

Max Activating Token Index: 498

Text #11

Max Range: 1.0739. Min Range: -1.0739

Max Act: 0.9517. Min Act: -0.0001

Data Index: 39156 (C4 (Web Text))

Max Activating Token Index: 267

Text #12

Max Range: 1.0739. Min Range: -1.0739

Max Act: 0.9537. Min Act: -0.0001

Data Index: 269131 (C4 (Web Text))

Max Activating Token Index: 465

Text #13

Max Range: 1.0739. Min Range: -1.0739

Max Act: 0.9413. Min Act: -0.0001

Data Index: 1349812 (C4 (Web Text))

Max Activating Token Index: 989

Text #14

Max Range: 1.0739. Min Range: -1.0739

Max Act: 0.8206. Min Act: -0.0001

Data Index: 351853 (C4 (Web Text))

Max Activating Token Index: 752

Text #15

Max Range: 1.0739. Min Range: -1.0739

Max Act: 0.9905. Min Act: -0.0001

Data Index: 840365 (C4 (Web Text))

Max Activating Token Index: 51

Text #16

Max Range: 1.0739. Min Range: -1.0739

Max Act: 0.9057. Min Act: -0.0001

Data Index: 484999 (C4 (Web Text))

Max Activating Token Index: 880

Text #17

Max Range: 1.0739. Min Range: -1.0739

Max Act: 0.9018. Min Act: -0.0001

Data Index: 1189963 (C4 (Web Text))

Max Activating Token Index: 464

Text #18

Max Range: 1.0739. Min Range: -1.0739

Max Act: 0.8924. Min Act: -0.0001

Data Index: 646380 (C4 (Web Text))

Max Activating Token Index: 279

Text #19

Max Range: 1.0739. Min Range: -1.0739

Max Act: 0.9244. Min Act: -0.0001

Data Index: 705670 (C4 (Web Text))

Max Activating Token Index: 896