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

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

Neuron 856 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.1648. Min Range: -1.1648

Max Act: 1.1648. Min Act: -0.0000

Data Index: 436752 (C4 (Web Text))

Max Activating Token Index: 848

Text #1

Max Range: 1.1648. Min Range: -1.1648

Max Act: 1.0830. Min Act: -0.0000

Data Index: 783601 (C4 (Web Text))

Max Activating Token Index: 369

Text #2

Max Range: 1.1648. Min Range: -1.1648

Max Act: 1.1606. Min Act: -0.0000

Data Index: 600617 (C4 (Web Text))

Max Activating Token Index: 180

Text #3

Max Range: 1.1648. Min Range: -1.1648

Max Act: 1.0149. Min Act: -0.0001

Data Index: 286525 (C4 (Web Text))

Max Activating Token Index: 639

Text #4

Max Range: 1.1648. Min Range: -1.1648

Max Act: 0.9842. Min Act: -0.0001

Data Index: 1036932 (C4 (Web Text))

Max Activating Token Index: 984

Text #5

Max Range: 1.1648. Min Range: -1.1648

Max Act: 1.0125. Min Act: -0.0000

Data Index: 1190635 (C4 (Web Text))

Max Activating Token Index: 866

Text #6

Max Range: 1.1648. Min Range: -1.1648

Max Act: 0.9628. Min Act: -0.0000

Data Index: 497008 (C4 (Web Text))

Max Activating Token Index: 891

Text #7

Max Range: 1.1648. Min Range: -1.1648

Max Act: 0.8960. Min Act: -0.0000

Data Index: 1179574 (C4 (Web Text))

Max Activating Token Index: 194

Text #8

Max Range: 1.1648. Min Range: -1.1648

Max Act: 0.8674. Min Act: -0.0000

Data Index: 329745 (C4 (Web Text))

Max Activating Token Index: 267

Text #9

Max Range: 1.1648. Min Range: -1.1648

Max Act: 0.8013. Min Act: -0.0000

Data Index: 809047 (C4 (Web Text))

Max Activating Token Index: 706

Text #10

Max Range: 1.1648. Min Range: -1.1648

Max Act: 0.8882. Min Act: -0.0000

Data Index: 1159 (C4 (Web Text))

Max Activating Token Index: 524

Text #11

Max Range: 1.1648. Min Range: -1.1648

Max Act: 0.8272. Min Act: -0.0001

Data Index: 328407 (C4 (Web Text))

Max Activating Token Index: 348

Text #12

Max Range: 1.1648. Min Range: -1.1648

Max Act: 0.8534. Min Act: -0.0001

Data Index: 320173 (C4 (Web Text))

Max Activating Token Index: 803

Text #13

Max Range: 1.1648. Min Range: -1.1648

Max Act: 0.8314. Min Act: -0.0000

Data Index: 697706 (C4 (Web Text))

Max Activating Token Index: 575

Text #14

Max Range: 1.1648. Min Range: -1.1648

Max Act: 0.7791. Min Act: -0.0000

Data Index: 630499 (C4 (Web Text))

Max Activating Token Index: 353

Text #15

Max Range: 1.1648. Min Range: -1.1648

Max Act: 0.8637. Min Act: -0.0000

Data Index: 1303849 (C4 (Web Text))

Max Activating Token Index: 406

Text #16

Max Range: 1.1648. Min Range: -1.1648

Max Act: 0.7976. Min Act: -0.0001

Data Index: 918308 (C4 (Web Text))

Max Activating Token Index: 163

Text #17

Max Range: 1.1648. Min Range: -1.1648

Max Act: 0.7449. Min Act: -0.0000

Data Index: 1246922 (C4 (Web Text))

Max Activating Token Index: 868

Text #18

Max Range: 1.1648. Min Range: -1.1648

Max Act: 0.7559. Min Act: -0.0000

Data Index: 383331 (C4 (Web Text))

Max Activating Token Index: 402

Text #19

Max Range: 1.1648. Min Range: -1.1648

Max Act: 0.7858. Min Act: -0.0000

Data Index: 972841 (C4 (Web Text))

Max Activating Token Index: 963