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

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

Neuron 578 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.6253. Min Range: -2.6253

Max Act: 2.6253. Min Act: -0.0000

Data Index: 782602 (C4 (Web Text))

Max Activating Token Index: 208

Text #1

Max Range: 2.6253. Min Range: -2.6253

Max Act: 2.0546. Min Act: -0.0000

Data Index: 1203653 (C4 (Web Text))

Max Activating Token Index: 123

Text #2

Max Range: 2.6253. Min Range: -2.6253

Max Act: 1.9961. Min Act: -0.0000

Data Index: 1347961 (C4 (Web Text))

Max Activating Token Index: 166

Text #3

Max Range: 2.6253. Min Range: -2.6253

Max Act: 2.2344. Min Act: -0.0000

Data Index: 1223440 (C4 (Web Text))

Max Activating Token Index: 385

Text #4

Max Range: 2.6253. Min Range: -2.6253

Max Act: 1.8418. Min Act: -0.0000

Data Index: 1024368 (C4 (Web Text))

Max Activating Token Index: 326

Text #5

Max Range: 2.6253. Min Range: -2.6253

Max Act: 1.6293. Min Act: -0.0000

Data Index: 1311859 (C4 (Web Text))

Max Activating Token Index: 332

Text #6

Max Range: 2.6253. Min Range: -2.6253

Max Act: 1.5966. Min Act: -0.0000

Data Index: 826878 (C4 (Web Text))

Max Activating Token Index: 1017

Text #7

Max Range: 2.6253. Min Range: -2.6253

Max Act: 1.3500. Min Act: -0.0000

Data Index: 471708 (C4 (Web Text))

Max Activating Token Index: 34

Text #8

Max Range: 2.6253. Min Range: -2.6253

Max Act: 1.3761. Min Act: -0.0000

Data Index: 431869 (C4 (Web Text))

Max Activating Token Index: 909

Text #9

Max Range: 2.6253. Min Range: -2.6253

Max Act: 1.4648. Min Act: -0.0000

Data Index: 747158 (C4 (Web Text))

Max Activating Token Index: 554

Text #10

Max Range: 2.6253. Min Range: -2.6253

Max Act: 1.2723. Min Act: -0.0000

Data Index: 1027246 (C4 (Web Text))

Max Activating Token Index: 284

Text #11

Max Range: 2.6253. Min Range: -2.6253

Max Act: 1.4503. Min Act: -0.0000

Data Index: 1280648 (C4 (Web Text))

Max Activating Token Index: 207

Text #12

Max Range: 2.6253. Min Range: -2.6253

Max Act: 1.3104. Min Act: -0.0000

Data Index: 1279396 (C4 (Web Text))

Max Activating Token Index: 307

Text #13

Max Range: 2.6253. Min Range: -2.6253

Max Act: 1.3372. Min Act: -0.0000

Data Index: 330263 (C4 (Web Text))

Max Activating Token Index: 581

Text #14

Max Range: 2.6253. Min Range: -2.6253

Max Act: 1.2261. Min Act: -0.0000

Data Index: 429086 (C4 (Web Text))

Max Activating Token Index: 39

Text #15

Max Range: 2.6253. Min Range: -2.6253

Max Act: 1.2596. Min Act: -0.0000

Data Index: 887103 (C4 (Web Text))

Max Activating Token Index: 225

Text #16

Max Range: 2.6253. Min Range: -2.6253

Max Act: 1.2053. Min Act: -0.0000

Data Index: 592471 (C4 (Web Text))

Max Activating Token Index: 108

Text #17

Max Range: 2.6253. Min Range: -2.6253

Max Act: 1.2404. Min Act: -0.0000

Data Index: 532438 (C4 (Web Text))

Max Activating Token Index: 13

Text #18

Max Range: 2.6253. Min Range: -2.6253

Max Act: 1.0541. Min Act: -0.0000

Data Index: 47720 (C4 (Web Text))

Max Activating Token Index: 280

Text #19

Max Range: 2.6253. Min Range: -2.6253

Max Act: 1.1010. Min Act: -0.0000

Data Index: 854519 (C4 (Web Text))

Max Activating Token Index: 94