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

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

Neuron 2345 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0177. Min Range: -1.0177

Max Act: 1.0177. Min Act: -0.0001

Data Index: 186802 (C4 (Web Text))

Max Activating Token Index: 597

Text #1

Max Range: 1.0177. Min Range: -1.0177

Max Act: 0.8468. Min Act: -0.0001

Data Index: 341160 (C4 (Web Text))

Max Activating Token Index: 784

Text #2

Max Range: 1.0177. Min Range: -1.0177

Max Act: 0.9027. Min Act: -0.0001

Data Index: 346866 (C4 (Web Text))

Max Activating Token Index: 693

Text #3

Max Range: 1.0177. Min Range: -1.0177

Max Act: 0.9292. Min Act: -0.0001

Data Index: 328160 (C4 (Web Text))

Max Activating Token Index: 416

Text #4

Max Range: 1.0177. Min Range: -1.0177

Max Act: 0.8497. Min Act: -0.0001

Data Index: 1238915 (C4 (Web Text))

Max Activating Token Index: 823

Text #5

Max Range: 1.0177. Min Range: -1.0177

Max Act: 0.8572. Min Act: -0.0001

Data Index: 490305 (C4 (Web Text))

Max Activating Token Index: 990

Text #6

Max Range: 1.0177. Min Range: -1.0177

Max Act: 0.8544. Min Act: -0.0001

Data Index: 357296 (C4 (Web Text))

Max Activating Token Index: 328

Text #7

Max Range: 1.0177. Min Range: -1.0177

Max Act: 0.8495. Min Act: -0.0001

Data Index: 1078008 (C4 (Web Text))

Max Activating Token Index: 124

Text #8

Max Range: 1.0177. Min Range: -1.0177

Max Act: 0.7873. Min Act: -0.0001

Data Index: 451591 (C4 (Web Text))

Max Activating Token Index: 957

Text #9

Max Range: 1.0177. Min Range: -1.0177

Max Act: 0.8411. Min Act: -0.0001

Data Index: 1022338 (C4 (Web Text))

Max Activating Token Index: 154

Text #10

Max Range: 1.0177. Min Range: -1.0177

Max Act: 0.8284. Min Act: -0.0001

Data Index: 512541 (C4 (Web Text))

Max Activating Token Index: 853

Text #11

Max Range: 1.0177. Min Range: -1.0177

Max Act: 0.8304. Min Act: -0.0001

Data Index: 1042527 (C4 (Web Text))

Max Activating Token Index: 410

Text #12

Max Range: 1.0177. Min Range: -1.0177

Max Act: 0.8554. Min Act: -0.0001

Data Index: 676449 (C4 (Web Text))

Max Activating Token Index: 255

Text #13

Max Range: 1.0177. Min Range: -1.0177

Max Act: 0.8479. Min Act: -0.0001

Data Index: 917643 (C4 (Web Text))

Max Activating Token Index: 703

Text #14

Max Range: 1.0177. Min Range: -1.0177

Max Act: 0.7901. Min Act: -0.0001

Data Index: 117880 (C4 (Web Text))

Max Activating Token Index: 208

Text #15

Max Range: 1.0177. Min Range: -1.0177

Max Act: 0.7881. Min Act: -0.0001

Data Index: 846556 (C4 (Web Text))

Max Activating Token Index: 384

Text #16

Max Range: 1.0177. Min Range: -1.0177

Max Act: 0.7395. Min Act: -0.0001

Data Index: 305864 (C4 (Web Text))

Max Activating Token Index: 799

Text #17

Max Range: 1.0177. Min Range: -1.0177

Max Act: 0.8156. Min Act: -0.0001

Data Index: 615694 (C4 (Web Text))

Max Activating Token Index: 661

Text #18

Max Range: 1.0177. Min Range: -1.0177

Max Act: 0.7823. Min Act: -0.0001

Data Index: 72015 (C4 (Web Text))

Max Activating Token Index: 926

Text #19

Max Range: 1.0177. Min Range: -1.0177

Max Act: 0.7801. Min Act: -0.0001

Data Index: 130048 (C4 (Web Text))

Max Activating Token Index: 964