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

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

Neuron 2987 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: 6.2004. Min Range: -6.2004

Max Act: 5.8527. Min Act: -0.0001

Data Index: 732446 (C4 (Web Text))

Max Activating Token Index: 369

Text #1

Max Range: 6.2004. Min Range: -6.2004

Max Act: 5.9153. Min Act: -0.0001

Data Index: 91725 (C4 (Web Text))

Max Activating Token Index: 10

Text #2

Max Range: 6.2004. Min Range: -6.2004

Max Act: 5.8771. Min Act: -0.0001

Data Index: 353185 (C4 (Web Text))

Max Activating Token Index: 611

Text #3

Max Range: 6.2004. Min Range: -6.2004

Max Act: 5.6625. Min Act: -0.0001

Data Index: 632701 (C4 (Web Text))

Max Activating Token Index: 603

Text #4

Max Range: 6.2004. Min Range: -6.2004

Max Act: 6.0341. Min Act: -0.0001

Data Index: 1234938 (C4 (Web Text))

Max Activating Token Index: 62

Text #5

Max Range: 6.2004. Min Range: -6.2004

Max Act: 6.0200. Min Act: -0.0001

Data Index: 419628 (C4 (Web Text))

Max Activating Token Index: 877

Text #6

Max Range: 6.2004. Min Range: -6.2004

Max Act: 6.2004. Min Act: -0.0001

Data Index: 64492 (C4 (Web Text))

Max Activating Token Index: 744

Text #7

Max Range: 6.2004. Min Range: -6.2004

Max Act: 5.8302. Min Act: -0.0001

Data Index: 162528 (C4 (Web Text))

Max Activating Token Index: 35

Text #8

Max Range: 6.2004. Min Range: -6.2004

Max Act: 5.5363. Min Act: -0.0001

Data Index: 344627 (C4 (Web Text))

Max Activating Token Index: 757

Text #9

Max Range: 6.2004. Min Range: -6.2004

Max Act: 5.5035. Min Act: -0.0001

Data Index: 777747 (C4 (Web Text))

Max Activating Token Index: 826

Text #10

Max Range: 6.2004. Min Range: -6.2004

Max Act: 5.1101. Min Act: -0.0001

Data Index: 1086684 (C4 (Web Text))

Max Activating Token Index: 941

Text #11

Max Range: 6.2004. Min Range: -6.2004

Max Act: 5.7637. Min Act: -0.0001

Data Index: 817240 (C4 (Web Text))

Max Activating Token Index: 530

Text #12

Max Range: 6.2004. Min Range: -6.2004

Max Act: 5.8768. Min Act: -0.0001

Data Index: 1225370 (C4 (Web Text))

Max Activating Token Index: 908

Text #13

Max Range: 6.2004. Min Range: -6.2004

Max Act: 5.7235. Min Act: -0.0001

Data Index: 209715 (C4 (Web Text))

Max Activating Token Index: 18

Text #14

Max Range: 6.2004. Min Range: -6.2004

Max Act: 5.3439. Min Act: -0.0001

Data Index: 90290 (C4 (Web Text))

Max Activating Token Index: 516

Text #15

Max Range: 6.2004. Min Range: -6.2004

Max Act: 5.7101. Min Act: -0.0001

Data Index: 966396 (C4 (Web Text))

Max Activating Token Index: 121

Text #16

Max Range: 6.2004. Min Range: -6.2004

Max Act: 5.3365. Min Act: -0.0001

Data Index: 1075179 (C4 (Web Text))

Max Activating Token Index: 784

Text #17

Max Range: 6.2004. Min Range: -6.2004

Max Act: 5.6757. Min Act: -0.0001

Data Index: 979477 (C4 (Web Text))

Max Activating Token Index: 828

Text #18

Max Range: 6.2004. Min Range: -6.2004

Max Act: 5.1569. Min Act: -0.0001

Data Index: 1355335 (C4 (Web Text))

Max Activating Token Index: 855

Text #19

Max Range: 6.2004. Min Range: -6.2004

Max Act: 5.3105. Min Act: -0.0001

Data Index: 849562 (C4 (Web Text))

Max Activating Token Index: 936