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

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

Neuron 2938 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.3630. Min Range: -1.3630

Max Act: 1.3630. Min Act: -0.0001

Data Index: 1041773 (C4 (Web Text))

Max Activating Token Index: 919

Text #1

Max Range: 1.3630. Min Range: -1.3630

Max Act: 1.3361. Min Act: -0.0001

Data Index: 696624 (C4 (Web Text))

Max Activating Token Index: 629

Text #2

Max Range: 1.3630. Min Range: -1.3630

Max Act: 1.0343. Min Act: -0.0001

Data Index: 827870 (C4 (Web Text))

Max Activating Token Index: 992

Text #3

Max Range: 1.3630. Min Range: -1.3630

Max Act: 1.0664. Min Act: -0.0001

Data Index: 497256 (C4 (Web Text))

Max Activating Token Index: 350

Text #4

Max Range: 1.3630. Min Range: -1.3630

Max Act: 1.0261. Min Act: -0.0001

Data Index: 926652 (C4 (Web Text))

Max Activating Token Index: 560

Text #5

Max Range: 1.3630. Min Range: -1.3630

Max Act: 1.0276. Min Act: -0.0001

Data Index: 309803 (C4 (Web Text))

Max Activating Token Index: 659

Text #6

Max Range: 1.3630. Min Range: -1.3630

Max Act: 1.0450. Min Act: -0.0001

Data Index: 75916 (C4 (Web Text))

Max Activating Token Index: 720

Text #7

Max Range: 1.3630. Min Range: -1.3630

Max Act: 1.0344. Min Act: -0.0001

Data Index: 1306331 (C4 (Web Text))

Max Activating Token Index: 655

Text #8

Max Range: 1.3630. Min Range: -1.3630

Max Act: 1.0837. Min Act: -0.0001

Data Index: 405356 (C4 (Web Text))

Max Activating Token Index: 287

Text #9

Max Range: 1.3630. Min Range: -1.3630

Max Act: 1.0180. Min Act: -0.0001

Data Index: 706247 (C4 (Web Text))

Max Activating Token Index: 852

Text #10

Max Range: 1.3630. Min Range: -1.3630

Max Act: 1.0040. Min Act: -0.0001

Data Index: 1242885 (C4 (Web Text))

Max Activating Token Index: 938

Text #11

Max Range: 1.3630. Min Range: -1.3630

Max Act: 0.9988. Min Act: -0.0001

Data Index: 332578 (C4 (Web Text))

Max Activating Token Index: 542

Text #12

Max Range: 1.3630. Min Range: -1.3630

Max Act: 1.0488. Min Act: -0.0001

Data Index: 744901 (C4 (Web Text))

Max Activating Token Index: 460

Text #13

Max Range: 1.3630. Min Range: -1.3630

Max Act: 0.9494. Min Act: -0.0001

Data Index: 336110 (C4 (Web Text))

Max Activating Token Index: 1022

Text #14

Max Range: 1.3630. Min Range: -1.3630

Max Act: 0.9215. Min Act: -0.0001

Data Index: 641756 (C4 (Web Text))

Max Activating Token Index: 192

Text #15

Max Range: 1.3630. Min Range: -1.3630

Max Act: 0.9420. Min Act: -0.0001

Data Index: 497012 (C4 (Web Text))

Max Activating Token Index: 344

Text #16

Max Range: 1.3630. Min Range: -1.3630

Max Act: 0.9634. Min Act: -0.0001

Data Index: 57288 (C4 (Web Text))

Max Activating Token Index: 104

Text #17

Max Range: 1.3630. Min Range: -1.3630

Max Act: 0.9053. Min Act: -0.0001

Data Index: 741925 (C4 (Web Text))

Max Activating Token Index: 594

Text #18

Max Range: 1.3630. Min Range: -1.3630

Max Act: 0.9200. Min Act: -0.0001

Data Index: 1335167 (C4 (Web Text))

Max Activating Token Index: 760

Text #19

Max Range: 1.3630. Min Range: -1.3630

Max Act: 0.8837. Min Act: -0.0001

Data Index: 266078 (C4 (Web Text))

Max Activating Token Index: 915