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

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

Neuron 2217 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: 0.3962. Min Range: -0.3962

Max Act: 0.3962. Min Act: -0.0000

Data Index: 886707 (C4 (Web Text))

Max Activating Token Index: 263

Text #1

Max Range: 0.3962. Min Range: -0.3962

Max Act: 0.3856. Min Act: -0.0000

Data Index: 685648 (C4 (Web Text))

Max Activating Token Index: 508

Text #2

Max Range: 0.3962. Min Range: -0.3962

Max Act: 0.3360. Min Act: -0.0001

Data Index: 466047 (C4 (Web Text))

Max Activating Token Index: 333

Text #3

Max Range: 0.3962. Min Range: -0.3962

Max Act: 0.3530. Min Act: -0.0001

Data Index: 565594 (C4 (Web Text))

Max Activating Token Index: 594

Text #4

Max Range: 0.3962. Min Range: -0.3962

Max Act: 0.3511. Min Act: -0.0000

Data Index: 570556 (C4 (Web Text))

Max Activating Token Index: 280

Text #5

Max Range: 0.3962. Min Range: -0.3962

Max Act: 0.3367. Min Act: -0.0001

Data Index: 702070 (C4 (Web Text))

Max Activating Token Index: 369

Text #6

Max Range: 0.3962. Min Range: -0.3962

Max Act: 0.3399. Min Act: -0.0000

Data Index: 1276530 (C4 (Web Text))

Max Activating Token Index: 273

Text #7

Max Range: 0.3962. Min Range: -0.3962

Max Act: 0.3504. Min Act: -0.0001

Data Index: 1048701 (C4 (Web Text))

Max Activating Token Index: 982

Text #8

Max Range: 0.3962. Min Range: -0.3962

Max Act: 0.3392. Min Act: -0.0000

Data Index: 869301 (C4 (Web Text))

Max Activating Token Index: 38

Text #9

Max Range: 0.3962. Min Range: -0.3962

Max Act: 0.3320. Min Act: 0.0000

Data Index: 386200 (C4 (Web Text))

Max Activating Token Index: 378

Text #10

Max Range: 0.3962. Min Range: -0.3962

Max Act: 0.3309. Min Act: -0.0000

Data Index: 655285 (C4 (Web Text))

Max Activating Token Index: 243

Text #11

Max Range: 0.3962. Min Range: -0.3962

Max Act: 0.3390. Min Act: -0.0000

Data Index: 1093958 (C4 (Web Text))

Max Activating Token Index: 353

Text #12

Max Range: 0.3962. Min Range: -0.3962

Max Act: 0.3390. Min Act: -0.0000

Data Index: 557008 (C4 (Web Text))

Max Activating Token Index: 464

Text #13

Max Range: 0.3962. Min Range: -0.3962

Max Act: 0.3129. Min Act: -0.0000

Data Index: 631700 (C4 (Web Text))

Max Activating Token Index: 417

Text #14

Max Range: 0.3962. Min Range: -0.3962

Max Act: 0.3115. Min Act: -0.0000

Data Index: 1101612 (C4 (Web Text))

Max Activating Token Index: 111

Text #15

Max Range: 0.3962. Min Range: -0.3962

Max Act: 0.3293. Min Act: -0.0000

Data Index: 153745 (C4 (Web Text))

Max Activating Token Index: 792

Text #16

Max Range: 0.3962. Min Range: -0.3962

Max Act: 0.3198. Min Act: -0.0000

Data Index: 1055538 (C4 (Web Text))

Max Activating Token Index: 869

Text #17

Max Range: 0.3962. Min Range: -0.3962

Max Act: 0.3055. Min Act: -0.0001

Data Index: 321467 (C4 (Web Text))

Max Activating Token Index: 34

Text #18

Max Range: 0.3962. Min Range: -0.3962

Max Act: 0.3110. Min Act: -0.0000

Data Index: 1005288 (C4 (Web Text))

Max Activating Token Index: 839

Text #19

Max Range: 0.3962. Min Range: -0.3962

Max Act: 0.3151. Min Act: -0.0000

Data Index: 814511 (C4 (Web Text))

Max Activating Token Index: 619