Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 1890 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 1.2362. Min Range: -1.2362

Max Act: 1.2362. Min Act: -0.0000

Data Index: 730104 (C4 (Web Text))

Max Activating Token Index: 182

Text #1

Max Range: 1.2362. Min Range: -1.2362

Max Act: 1.2326. Min Act: -0.0000

Data Index: 665225 (C4 (Web Text))

Max Activating Token Index: 736

Text #2

Max Range: 1.2362. Min Range: -1.2362

Max Act: 1.1439. Min Act: -0.0000

Data Index: 339911 (C4 (Web Text))

Max Activating Token Index: 512

Text #3

Max Range: 1.2362. Min Range: -1.2362

Max Act: 1.0872. Min Act: -0.0000

Data Index: 891612 (C4 (Web Text))

Max Activating Token Index: 452

Text #4

Max Range: 1.2362. Min Range: -1.2362

Max Act: 0.9479. Min Act: -0.0000

Data Index: 146690 (C4 (Web Text))

Max Activating Token Index: 157

Text #5

Max Range: 1.2362. Min Range: -1.2362

Max Act: 0.9547. Min Act: -0.0000

Data Index: 9485 (C4 (Web Text))

Max Activating Token Index: 464

Text #6

Max Range: 1.2362. Min Range: -1.2362

Max Act: 0.9272. Min Act: -0.0000

Data Index: 1209131 (C4 (Web Text))

Max Activating Token Index: 880

Text #7

Max Range: 1.2362. Min Range: -1.2362

Max Act: 0.9909. Min Act: -0.0000

Data Index: 281912 (C4 (Web Text))

Max Activating Token Index: 584

Text #8

Max Range: 1.2362. Min Range: -1.2362

Max Act: 0.9777. Min Act: -0.0000

Data Index: 561028 (C4 (Web Text))

Max Activating Token Index: 146

Text #9

Max Range: 1.2362. Min Range: -1.2362

Max Act: 0.9302. Min Act: -0.0000

Data Index: 734304 (C4 (Web Text))

Max Activating Token Index: 277

Text #10

Max Range: 1.2362. Min Range: -1.2362

Max Act: 0.9556. Min Act: -0.0000

Data Index: 501575 (C4 (Web Text))

Max Activating Token Index: 905

Text #11

Max Range: 1.2362. Min Range: -1.2362

Max Act: 0.9275. Min Act: -0.0000

Data Index: 1177285 (C4 (Web Text))

Max Activating Token Index: 542

Text #12

Max Range: 1.2362. Min Range: -1.2362

Max Act: 0.9673. Min Act: -0.0000

Data Index: 771598 (C4 (Web Text))

Max Activating Token Index: 362

Text #13

Max Range: 1.2362. Min Range: -1.2362

Max Act: 0.9874. Min Act: -0.0000

Data Index: 1185678 (C4 (Web Text))

Max Activating Token Index: 385

Text #14

Max Range: 1.2362. Min Range: -1.2362

Max Act: 0.9229. Min Act: -0.0000

Data Index: 361362 (C4 (Web Text))

Max Activating Token Index: 595

Text #15

Max Range: 1.2362. Min Range: -1.2362

Max Act: 0.9674. Min Act: -0.0000

Data Index: 162801 (C4 (Web Text))

Max Activating Token Index: 551

Text #16

Max Range: 1.2362. Min Range: -1.2362

Max Act: 0.9805. Min Act: -0.0000

Data Index: 1337580 (C4 (Web Text))

Max Activating Token Index: 512

Text #17

Max Range: 1.2362. Min Range: -1.2362

Max Act: 0.9012. Min Act: -0.0000

Data Index: 25049 (C4 (Web Text))

Max Activating Token Index: 951

Text #18

Max Range: 1.2362. Min Range: -1.2362

Max Act: 0.8771. Min Act: -0.0000

Data Index: 80364 (C4 (Web Text))

Max Activating Token Index: 108

Text #19

Max Range: 1.2362. Min Range: -1.2362

Max Act: 1.0664. Min Act: -0.0000

Data Index: 1088011 (C4 (Web Text))

Max Activating Token Index: 175