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

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

Neuron 2585 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: 0.3890. Min Range: -0.3890

Max Act: 0.3890. Min Act: -0.0001

Data Index: 794054 (C4 (Web Text))

Max Activating Token Index: 550

Text #1

Max Range: 0.3890. Min Range: -0.3890

Max Act: 0.3757. Min Act: -0.0001

Data Index: 188733 (C4 (Web Text))

Max Activating Token Index: 285

Text #2

Max Range: 0.3890. Min Range: -0.3890

Max Act: 0.3482. Min Act: -0.0001

Data Index: 1165315 (C4 (Web Text))

Max Activating Token Index: 361

Text #3

Max Range: 0.3890. Min Range: -0.3890

Max Act: 0.3344. Min Act: -0.0001

Data Index: 508691 (C4 (Web Text))

Max Activating Token Index: 446

Text #4

Max Range: 0.3890. Min Range: -0.3890

Max Act: 0.3227. Min Act: -0.0001

Data Index: 994334 (C4 (Web Text))

Max Activating Token Index: 945

Text #5

Max Range: 0.3890. Min Range: -0.3890

Max Act: 0.3173. Min Act: -0.0001

Data Index: 1137127 (C4 (Web Text))

Max Activating Token Index: 829

Text #6

Max Range: 0.3890. Min Range: -0.3890

Max Act: 0.3243. Min Act: -0.0001

Data Index: 61490 (C4 (Web Text))

Max Activating Token Index: 213

Text #7

Max Range: 0.3890. Min Range: -0.3890

Max Act: 0.3057. Min Act: -0.0001

Data Index: 465609 (C4 (Web Text))

Max Activating Token Index: 267

Text #8

Max Range: 0.3890. Min Range: -0.3890

Max Act: 0.3340. Min Act: -0.0001

Data Index: 1307222 (C4 (Web Text))

Max Activating Token Index: 186

Text #9

Max Range: 0.3890. Min Range: -0.3890

Max Act: 0.3235. Min Act: -0.0001

Data Index: 57580 (C4 (Web Text))

Max Activating Token Index: 209

Text #10

Max Range: 0.3890. Min Range: -0.3890

Max Act: 0.3073. Min Act: -0.0001

Data Index: 1227417 (C4 (Web Text))

Max Activating Token Index: 463

Text #11

Max Range: 0.3890. Min Range: -0.3890

Max Act: 0.3028. Min Act: -0.0001

Data Index: 1342284 (C4 (Web Text))

Max Activating Token Index: 559

Text #12

Max Range: 0.3890. Min Range: -0.3890

Max Act: 0.2980. Min Act: -0.0001

Data Index: 777499 (C4 (Web Text))

Max Activating Token Index: 782

Text #13

Max Range: 0.3890. Min Range: -0.3890

Max Act: 0.2917. Min Act: -0.0001

Data Index: 982328 (C4 (Web Text))

Max Activating Token Index: 575

Text #14

Max Range: 0.3890. Min Range: -0.3890

Max Act: 0.2798. Min Act: -0.0000

Data Index: 227350 (C4 (Web Text))

Max Activating Token Index: 420

Text #15

Max Range: 0.3890. Min Range: -0.3890

Max Act: 0.2879. Min Act: -0.0001

Data Index: 208234 (C4 (Web Text))

Max Activating Token Index: 559

Text #16

Max Range: 0.3890. Min Range: -0.3890

Max Act: 0.2746. Min Act: -0.0001

Data Index: 290616 (C4 (Web Text))

Max Activating Token Index: 293

Text #17

Max Range: 0.3890. Min Range: -0.3890

Max Act: 0.2391. Min Act: -0.0001

Data Index: 760012 (C4 (Web Text))

Max Activating Token Index: 608

Text #18

Max Range: 0.3890. Min Range: -0.3890

Max Act: 0.2536. Min Act: -0.0001

Data Index: 424686 (C4 (Web Text))

Max Activating Token Index: 917

Text #19

Max Range: 0.3890. Min Range: -0.3890

Max Act: 0.2493. Min Act: -0.0001

Data Index: 390557 (C4 (Web Text))

Max Activating Token Index: 260