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

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

Neuron 2860 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3351. Min Range: -0.3351

Max Act: 0.3231. Min Act: -0.0002

Data Index: 1236901 (C4 (Web Text))

Max Activating Token Index: 664

Text #1

Max Range: 0.3351. Min Range: -0.3351

Max Act: 0.3351. Min Act: -0.0001

Data Index: 530794 (C4 (Web Text))

Max Activating Token Index: 649

Text #2

Max Range: 0.3351. Min Range: -0.3351

Max Act: 0.3049. Min Act: -0.0002

Data Index: 739110 (C4 (Web Text))

Max Activating Token Index: 754

Text #3

Max Range: 0.3351. Min Range: -0.3351

Max Act: 0.2995. Min Act: -0.0002

Data Index: 1284657 (C4 (Web Text))

Max Activating Token Index: 26

Text #4

Max Range: 0.3351. Min Range: -0.3351

Max Act: 0.3088. Min Act: -0.0002

Data Index: 534669 (C4 (Web Text))

Max Activating Token Index: 451

Text #5

Max Range: 0.3351. Min Range: -0.3351

Max Act: 0.3220. Min Act: -0.0001

Data Index: 762215 (C4 (Web Text))

Max Activating Token Index: 761

Text #6

Max Range: 0.3351. Min Range: -0.3351

Max Act: 0.3070. Min Act: -0.0002

Data Index: 174201 (C4 (Web Text))

Max Activating Token Index: 8

Text #7

Max Range: 0.3351. Min Range: -0.3351

Max Act: 0.3145. Min Act: -0.0002

Data Index: 327700 (C4 (Web Text))

Max Activating Token Index: 852

Text #8

Max Range: 0.3351. Min Range: -0.3351

Max Act: 0.2977. Min Act: -0.0002

Data Index: 725700 (C4 (Web Text))

Max Activating Token Index: 467

Text #9

Max Range: 0.3351. Min Range: -0.3351

Max Act: 0.2829. Min Act: -0.0002

Data Index: 398110 (C4 (Web Text))

Max Activating Token Index: 435

Text #10

Max Range: 0.3351. Min Range: -0.3351

Max Act: 0.2911. Min Act: -0.0002

Data Index: 846172 (C4 (Web Text))

Max Activating Token Index: 891

Text #11

Max Range: 0.3351. Min Range: -0.3351

Max Act: 0.3074. Min Act: -0.0002

Data Index: 1018264 (C4 (Web Text))

Max Activating Token Index: 485

Text #12

Max Range: 0.3351. Min Range: -0.3351

Max Act: 0.2754. Min Act: -0.0002

Data Index: 1336321 (C4 (Web Text))

Max Activating Token Index: 841

Text #13

Max Range: 0.3351. Min Range: -0.3351

Max Act: 0.2844. Min Act: -0.0002

Data Index: 808780 (C4 (Web Text))

Max Activating Token Index: 294

Text #14

Max Range: 0.3351. Min Range: -0.3351

Max Act: 0.2845. Min Act: -0.0002

Data Index: 1252466 (C4 (Web Text))

Max Activating Token Index: 510

Text #15

Max Range: 0.3351. Min Range: -0.3351

Max Act: 0.2743. Min Act: -0.0002

Data Index: 659141 (C4 (Web Text))

Max Activating Token Index: 405

Text #16

Max Range: 0.3351. Min Range: -0.3351

Max Act: 0.2825. Min Act: -0.0002

Data Index: 274184 (C4 (Web Text))

Max Activating Token Index: 436

Text #17

Max Range: 0.3351. Min Range: -0.3351

Max Act: 0.3017. Min Act: -0.0002

Data Index: 1217592 (C4 (Web Text))

Max Activating Token Index: 940

Text #18

Max Range: 0.3351. Min Range: -0.3351

Max Act: 0.2796. Min Act: -0.0001

Data Index: 185935 (C4 (Web Text))

Max Activating Token Index: 170

Text #19

Max Range: 0.3351. Min Range: -0.3351

Max Act: 0.2771. Min Act: -0.0002

Data Index: 690600 (C4 (Web Text))

Max Activating Token Index: 977