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

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

Neuron 3383 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: 0.7847. Min Range: -0.7847

Max Act: 0.7847. Min Act: -0.0000

Data Index: 1165059 (C4 (Web Text))

Max Activating Token Index: 543

Text #1

Max Range: 0.7847. Min Range: -0.7847

Max Act: 0.6685. Min Act: -0.0000

Data Index: 413620 (C4 (Web Text))

Max Activating Token Index: 179

Text #2

Max Range: 0.7847. Min Range: -0.7847

Max Act: 0.6855. Min Act: -0.0000

Data Index: 339636 (C4 (Web Text))

Max Activating Token Index: 502

Text #3

Max Range: 0.7847. Min Range: -0.7847

Max Act: 0.6827. Min Act: -0.0000

Data Index: 670381 (C4 (Web Text))

Max Activating Token Index: 545

Text #4

Max Range: 0.7847. Min Range: -0.7847

Max Act: 0.6740. Min Act: -0.0000

Data Index: 975494 (C4 (Web Text))

Max Activating Token Index: 392

Text #5

Max Range: 0.7847. Min Range: -0.7847

Max Act: 0.6171. Min Act: -0.0000

Data Index: 975400 (C4 (Web Text))

Max Activating Token Index: 556

Text #6

Max Range: 0.7847. Min Range: -0.7847

Max Act: 0.6200. Min Act: -0.0000

Data Index: 183412 (C4 (Web Text))

Max Activating Token Index: 565

Text #7

Max Range: 0.7847. Min Range: -0.7847

Max Act: 0.6057. Min Act: -0.0000

Data Index: 495680 (C4 (Web Text))

Max Activating Token Index: 1005

Text #8

Max Range: 0.7847. Min Range: -0.7847

Max Act: 0.5400. Min Act: -0.0000

Data Index: 672560 (C4 (Web Text))

Max Activating Token Index: 696

Text #9

Max Range: 0.7847. Min Range: -0.7847

Max Act: 0.5652. Min Act: -0.0000

Data Index: 801158 (C4 (Web Text))

Max Activating Token Index: 342

Text #10

Max Range: 0.7847. Min Range: -0.7847

Max Act: 0.5520. Min Act: -0.0000

Data Index: 1103897 (C4 (Web Text))

Max Activating Token Index: 426

Text #11

Max Range: 0.7847. Min Range: -0.7847

Max Act: 0.5641. Min Act: -0.0000

Data Index: 507152 (C4 (Web Text))

Max Activating Token Index: 656

Text #12

Max Range: 0.7847. Min Range: -0.7847

Max Act: 0.5602. Min Act: -0.0000

Data Index: 302517 (C4 (Web Text))

Max Activating Token Index: 364

Text #13

Max Range: 0.7847. Min Range: -0.7847

Max Act: 0.5354. Min Act: -0.0000

Data Index: 495165 (C4 (Web Text))

Max Activating Token Index: 573

Text #14

Max Range: 0.7847. Min Range: -0.7847

Max Act: 0.5464. Min Act: -0.0000

Data Index: 145226 (C4 (Web Text))

Max Activating Token Index: 163

Text #15

Max Range: 0.7847. Min Range: -0.7847

Max Act: 0.5467. Min Act: -0.0000

Data Index: 1289960 (C4 (Web Text))

Max Activating Token Index: 146

Text #16

Max Range: 0.7847. Min Range: -0.7847

Max Act: 0.5520. Min Act: -0.0000

Data Index: 213182 (C4 (Web Text))

Max Activating Token Index: 105

Text #17

Max Range: 0.7847. Min Range: -0.7847

Max Act: 0.5534. Min Act: -0.0000

Data Index: 893351 (C4 (Web Text))

Max Activating Token Index: 832

Text #18

Max Range: 0.7847. Min Range: -0.7847

Max Act: 0.5304. Min Act: -0.0000

Data Index: 1142321 (C4 (Web Text))

Max Activating Token Index: 399

Text #19

Max Range: 0.7847. Min Range: -0.7847

Max Act: 0.5483. Min Act: -0.0000

Data Index: 971049 (C4 (Web Text))

Max Activating Token Index: 868