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

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

Neuron 1115 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: 0.6359. Min Range: -0.6359

Max Act: 0.6298. Min Act: -0.0001

Data Index: 108143 (C4 (Web Text))

Max Activating Token Index: 925

Text #1

Max Range: 0.6359. Min Range: -0.6359

Max Act: 0.6062. Min Act: -0.0001

Data Index: 662637 (C4 (Web Text))

Max Activating Token Index: 853

Text #2

Max Range: 0.6359. Min Range: -0.6359

Max Act: 0.6359. Min Act: -0.0001

Data Index: 887294 (C4 (Web Text))

Max Activating Token Index: 963

Text #3

Max Range: 0.6359. Min Range: -0.6359

Max Act: 0.5526. Min Act: -0.0001

Data Index: 696021 (C4 (Web Text))

Max Activating Token Index: 912

Text #4

Max Range: 0.6359. Min Range: -0.6359

Max Act: 0.5724. Min Act: -0.0001

Data Index: 597740 (C4 (Web Text))

Max Activating Token Index: 881

Text #5

Max Range: 0.6359. Min Range: -0.6359

Max Act: 0.6180. Min Act: -0.0001

Data Index: 375495 (C4 (Web Text))

Max Activating Token Index: 988

Text #6

Max Range: 0.6359. Min Range: -0.6359

Max Act: 0.5654. Min Act: -0.0001

Data Index: 367244 (C4 (Web Text))

Max Activating Token Index: 939

Text #7

Max Range: 0.6359. Min Range: -0.6359

Max Act: 0.6166. Min Act: -0.0001

Data Index: 1106355 (C4 (Web Text))

Max Activating Token Index: 696

Text #8

Max Range: 0.6359. Min Range: -0.6359

Max Act: 0.5843. Min Act: -0.0001

Data Index: 46239 (C4 (Web Text))

Max Activating Token Index: 916

Text #9

Max Range: 0.6359. Min Range: -0.6359

Max Act: 0.5870. Min Act: -0.0001

Data Index: 348231 (C4 (Web Text))

Max Activating Token Index: 996

Text #10

Max Range: 0.6359. Min Range: -0.6359

Max Act: 0.5831. Min Act: -0.0001

Data Index: 788374 (C4 (Web Text))

Max Activating Token Index: 943

Text #11

Max Range: 0.6359. Min Range: -0.6359

Max Act: 0.5397. Min Act: -0.0001

Data Index: 1246735 (C4 (Web Text))

Max Activating Token Index: 759

Text #12

Max Range: 0.6359. Min Range: -0.6359

Max Act: 0.5607. Min Act: -0.0001

Data Index: 421666 (C4 (Web Text))

Max Activating Token Index: 767

Text #13

Max Range: 0.6359. Min Range: -0.6359

Max Act: 0.5817. Min Act: -0.0001

Data Index: 778333 (C4 (Web Text))

Max Activating Token Index: 1007

Text #14

Max Range: 0.6359. Min Range: -0.6359

Max Act: 0.5608. Min Act: -0.0001

Data Index: 121359 (C4 (Web Text))

Max Activating Token Index: 864

Text #15

Max Range: 0.6359. Min Range: -0.6359

Max Act: 0.5625. Min Act: -0.0001

Data Index: 878509 (C4 (Web Text))

Max Activating Token Index: 698

Text #16

Max Range: 0.6359. Min Range: -0.6359

Max Act: 0.5210. Min Act: -0.0001

Data Index: 951322 (C4 (Web Text))

Max Activating Token Index: 853

Text #17

Max Range: 0.6359. Min Range: -0.6359

Max Act: 0.5890. Min Act: -0.0001

Data Index: 293073 (C4 (Web Text))

Max Activating Token Index: 910

Text #18

Max Range: 0.6359. Min Range: -0.6359

Max Act: 0.5553. Min Act: -0.0001

Data Index: 1248021 (C4 (Web Text))

Max Activating Token Index: 875

Text #19

Max Range: 0.6359. Min Range: -0.6359

Max Act: 0.5642. Min Act: -0.0001

Data Index: 423925 (C4 (Web Text))

Max Activating Token Index: 957