Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 3385 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 2.0721. Min Range: -2.0721

Max Act: 2.0721. Min Act: -0.0000

Data Index: 109757 (C4 (Web Text))

Max Activating Token Index: 102

Text #1

Max Range: 2.0721. Min Range: -2.0721

Max Act: 1.7898. Min Act: -0.0000

Data Index: 193500 (C4 (Web Text))

Max Activating Token Index: 274

Text #2

Max Range: 2.0721. Min Range: -2.0721

Max Act: 1.5676. Min Act: -0.0000

Data Index: 1063855 (C4 (Web Text))

Max Activating Token Index: 314

Text #3

Max Range: 2.0721. Min Range: -2.0721

Max Act: 1.5533. Min Act: -0.0000

Data Index: 705062 (C4 (Web Text))

Max Activating Token Index: 834

Text #4

Max Range: 2.0721. Min Range: -2.0721

Max Act: 1.4250. Min Act: -0.0000

Data Index: 216231 (C4 (Web Text))

Max Activating Token Index: 267

Text #5

Max Range: 2.0721. Min Range: -2.0721

Max Act: 1.3783. Min Act: -0.0000

Data Index: 671495 (C4 (Web Text))

Max Activating Token Index: 294

Text #6

Max Range: 2.0721. Min Range: -2.0721

Max Act: 1.2069. Min Act: -0.0000

Data Index: 391002 (C4 (Web Text))

Max Activating Token Index: 938

Text #7

Max Range: 2.0721. Min Range: -2.0721

Max Act: 1.1750. Min Act: -0.0000

Data Index: 1096484 (C4 (Web Text))

Max Activating Token Index: 963

Text #8

Max Range: 2.0721. Min Range: -2.0721

Max Act: 1.4125. Min Act: -0.0000

Data Index: 35140 (C4 (Web Text))

Max Activating Token Index: 342

Text #9

Max Range: 2.0721. Min Range: -2.0721

Max Act: 1.2197. Min Act: -0.0000

Data Index: 1037056 (C4 (Web Text))

Max Activating Token Index: 390

Text #10

Max Range: 2.0721. Min Range: -2.0721

Max Act: 1.3325. Min Act: -0.0000

Data Index: 276277 (C4 (Web Text))

Max Activating Token Index: 299

Text #11

Max Range: 2.0721. Min Range: -2.0721

Max Act: 1.1897. Min Act: -0.0000

Data Index: 513651 (C4 (Web Text))

Max Activating Token Index: 817

Text #12

Max Range: 2.0721. Min Range: -2.0721

Max Act: 1.3135. Min Act: -0.0000

Data Index: 886821 (C4 (Web Text))

Max Activating Token Index: 395

Text #13

Max Range: 2.0721. Min Range: -2.0721

Max Act: 1.3489. Min Act: -0.0000

Data Index: 1202684 (C4 (Web Text))

Max Activating Token Index: 379

Text #14

Max Range: 2.0721. Min Range: -2.0721

Max Act: 1.2640. Min Act: -0.0000

Data Index: 237688 (C4 (Web Text))

Max Activating Token Index: 704

Text #15

Max Range: 2.0721. Min Range: -2.0721

Max Act: 1.6044. Min Act: -0.0000

Data Index: 1065451 (C4 (Web Text))

Max Activating Token Index: 580

Text #16

Max Range: 2.0721. Min Range: -2.0721

Max Act: 1.4549. Min Act: -0.0000

Data Index: 1123207 (C4 (Web Text))

Max Activating Token Index: 1011

Text #17

Max Range: 2.0721. Min Range: -2.0721

Max Act: 1.3416. Min Act: -0.0000

Data Index: 712225 (C4 (Web Text))

Max Activating Token Index: 346

Text #18

Max Range: 2.0721. Min Range: -2.0721

Max Act: 1.2322. Min Act: -0.0000

Data Index: 1031956 (C4 (Web Text))

Max Activating Token Index: 520

Text #19

Max Range: 2.0721. Min Range: -2.0721

Max Act: 1.2244. Min Act: -0.0000

Data Index: 924975 (C4 (Web Text))

Max Activating Token Index: 303