Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 12 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 2.1743. Min Range: -2.1743

Max Act: 2.1743. Min Act: -0.0000

Data Index: 100678 (C4 (Web Text))

Max Activating Token Index: 697

Text #1

Max Range: 2.1743. Min Range: -2.1743

Max Act: 2.0384. Min Act: -0.0000

Data Index: 971725 (C4 (Web Text))

Max Activating Token Index: 932

Text #2

Max Range: 2.1743. Min Range: -2.1743

Max Act: 2.1105. Min Act: -0.0000

Data Index: 465600 (C4 (Web Text))

Max Activating Token Index: 229

Text #3

Max Range: 2.1743. Min Range: -2.1743

Max Act: 2.1336. Min Act: -0.0000

Data Index: 1133156 (C4 (Web Text))

Max Activating Token Index: 355

Text #4

Max Range: 2.1743. Min Range: -2.1743

Max Act: 2.0500. Min Act: -0.0000

Data Index: 958841 (C4 (Web Text))

Max Activating Token Index: 693

Text #5

Max Range: 2.1743. Min Range: -2.1743

Max Act: 2.0256. Min Act: -0.0000

Data Index: 795534 (C4 (Web Text))

Max Activating Token Index: 538

Text #6

Max Range: 2.1743. Min Range: -2.1743

Max Act: 1.9564. Min Act: -0.0000

Data Index: 160878 (C4 (Web Text))

Max Activating Token Index: 33

Text #7

Max Range: 2.1743. Min Range: -2.1743

Max Act: 1.9379. Min Act: -0.0000

Data Index: 258364 (C4 (Web Text))

Max Activating Token Index: 321

Text #8

Max Range: 2.1743. Min Range: -2.1743

Max Act: 1.9389. Min Act: -0.0000

Data Index: 56532 (C4 (Web Text))

Max Activating Token Index: 476

Text #9

Max Range: 2.1743. Min Range: -2.1743

Max Act: 1.9251. Min Act: -0.0000

Data Index: 719364 (C4 (Web Text))

Max Activating Token Index: 302

Text #10

Max Range: 2.1743. Min Range: -2.1743

Max Act: 1.9266. Min Act: -0.0000

Data Index: 503491 (C4 (Web Text))

Max Activating Token Index: 126

Text #11

Max Range: 2.1743. Min Range: -2.1743

Max Act: 1.7859. Min Act: -0.0000

Data Index: 253792 (C4 (Web Text))

Max Activating Token Index: 209

Text #12

Max Range: 2.1743. Min Range: -2.1743

Max Act: 1.8991. Min Act: -0.0000

Data Index: 182789 (C4 (Web Text))

Max Activating Token Index: 566

Text #13

Max Range: 2.1743. Min Range: -2.1743

Max Act: 1.8924. Min Act: -0.0000

Data Index: 1262557 (C4 (Web Text))

Max Activating Token Index: 597

Text #14

Max Range: 2.1743. Min Range: -2.1743

Max Act: 1.8765. Min Act: -0.0000

Data Index: 369950 (C4 (Web Text))

Max Activating Token Index: 252

Text #15

Max Range: 2.1743. Min Range: -2.1743

Max Act: 1.8782. Min Act: -0.0000

Data Index: 197499 (C4 (Web Text))

Max Activating Token Index: 185

Text #16

Max Range: 2.1743. Min Range: -2.1743

Max Act: 1.7670. Min Act: -0.0000

Data Index: 682731 (C4 (Web Text))

Max Activating Token Index: 362

Text #17

Max Range: 2.1743. Min Range: -2.1743

Max Act: 1.8480. Min Act: -0.0000

Data Index: 940446 (C4 (Web Text))

Max Activating Token Index: 333

Text #18

Max Range: 2.1743. Min Range: -2.1743

Max Act: 1.7300. Min Act: -0.0000

Data Index: 779131 (C4 (Web Text))

Max Activating Token Index: 32

Text #19

Max Range: 2.1743. Min Range: -2.1743

Max Act: 1.7153. Min Act: -0.0000

Data Index: 36284 (C4 (Web Text))

Max Activating Token Index: 236