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

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

Neuron 2856 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.8320. Min Range: -0.8320

Max Act: 0.6550. Min Act: -0.0001

Data Index: 1053402 (C4 (Web Text))

Max Activating Token Index: 600

Text #1

Max Range: 0.8320. Min Range: -0.8320

Max Act: 0.7307. Min Act: -0.0001

Data Index: 1006847 (C4 (Web Text))

Max Activating Token Index: 694

Text #2

Max Range: 0.8320. Min Range: -0.8320

Max Act: 0.8320. Min Act: -0.0001

Data Index: 581893 (C4 (Web Text))

Max Activating Token Index: 99

Text #3

Max Range: 0.8320. Min Range: -0.8320

Max Act: 0.7850. Min Act: -0.0001

Data Index: 470385 (C4 (Web Text))

Max Activating Token Index: 435

Text #4

Max Range: 0.8320. Min Range: -0.8320

Max Act: 0.7323. Min Act: -0.0001

Data Index: 881490 (C4 (Web Text))

Max Activating Token Index: 891

Text #5

Max Range: 0.8320. Min Range: -0.8320

Max Act: 0.7286. Min Act: -0.0001

Data Index: 221237 (C4 (Web Text))

Max Activating Token Index: 1017

Text #6

Max Range: 0.8320. Min Range: -0.8320

Max Act: 0.7190. Min Act: -0.0001

Data Index: 694733 (C4 (Web Text))

Max Activating Token Index: 697

Text #7

Max Range: 0.8320. Min Range: -0.8320

Max Act: 0.7065. Min Act: -0.0001

Data Index: 685027 (C4 (Web Text))

Max Activating Token Index: 430

Text #8

Max Range: 0.8320. Min Range: -0.8320

Max Act: 0.7349. Min Act: -0.0001

Data Index: 244626 (C4 (Web Text))

Max Activating Token Index: 827

Text #9

Max Range: 0.8320. Min Range: -0.8320

Max Act: 0.6234. Min Act: -0.0001

Data Index: 877387 (C4 (Web Text))

Max Activating Token Index: 267

Text #10

Max Range: 0.8320. Min Range: -0.8320

Max Act: 0.7027. Min Act: -0.0001

Data Index: 302792 (C4 (Web Text))

Max Activating Token Index: 700

Text #11

Max Range: 0.8320. Min Range: -0.8320

Max Act: 0.7392. Min Act: -0.0001

Data Index: 1149154 (C4 (Web Text))

Max Activating Token Index: 713

Text #12

Max Range: 0.8320. Min Range: -0.8320

Max Act: 0.7089. Min Act: -0.0001

Data Index: 345141 (C4 (Web Text))

Max Activating Token Index: 73

Text #13

Max Range: 0.8320. Min Range: -0.8320

Max Act: 0.6907. Min Act: -0.0001

Data Index: 587423 (C4 (Web Text))

Max Activating Token Index: 298

Text #14

Max Range: 0.8320. Min Range: -0.8320

Max Act: 0.7780. Min Act: -0.0001

Data Index: 178335 (C4 (Web Text))

Max Activating Token Index: 571

Text #15

Max Range: 0.8320. Min Range: -0.8320

Max Act: 0.6956. Min Act: -0.0001

Data Index: 508670 (C4 (Web Text))

Max Activating Token Index: 50

Text #16

Max Range: 0.8320. Min Range: -0.8320

Max Act: 0.6721. Min Act: -0.0001

Data Index: 939991 (C4 (Web Text))

Max Activating Token Index: 570

Text #17

Max Range: 0.8320. Min Range: -0.8320

Max Act: 0.7280. Min Act: -0.0001

Data Index: 239002 (C4 (Web Text))

Max Activating Token Index: 757

Text #18

Max Range: 0.8320. Min Range: -0.8320

Max Act: 0.7716. Min Act: -0.0001

Data Index: 883928 (C4 (Web Text))

Max Activating Token Index: 775

Text #19

Max Range: 0.8320. Min Range: -0.8320

Max Act: 0.6141. Min Act: -0.0001

Data Index: 384838 (C4 (Web Text))

Max Activating Token Index: 18