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

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

Neuron 4873 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: 2.6385. Min Range: -2.6385

Max Act: 2.6385. Min Act: -0.0000

Data Index: 166757 (C4 (Web Text))

Max Activating Token Index: 81

Text #1

Max Range: 2.6385. Min Range: -2.6385

Max Act: 2.5087. Min Act: -0.0000

Data Index: 311159 (C4 (Web Text))

Max Activating Token Index: 474

Text #2

Max Range: 2.6385. Min Range: -2.6385

Max Act: 2.3168. Min Act: -0.0000

Data Index: 876135 (C4 (Web Text))

Max Activating Token Index: 262

Text #3

Max Range: 2.6385. Min Range: -2.6385

Max Act: 2.3353. Min Act: -0.0000

Data Index: 641985 (C4 (Web Text))

Max Activating Token Index: 934

Text #4

Max Range: 2.6385. Min Range: -2.6385

Max Act: 2.3404. Min Act: -0.0000

Data Index: 451474 (C4 (Web Text))

Max Activating Token Index: 177

Text #5

Max Range: 2.6385. Min Range: -2.6385

Max Act: 2.2003. Min Act: -0.0000

Data Index: 534014 (C4 (Web Text))

Max Activating Token Index: 384

Text #6

Max Range: 2.6385. Min Range: -2.6385

Max Act: 2.3146. Min Act: -0.0000

Data Index: 29891 (C4 (Web Text))

Max Activating Token Index: 158

Text #7

Max Range: 2.6385. Min Range: -2.6385

Max Act: 2.3071. Min Act: -0.0000

Data Index: 252794 (C4 (Web Text))

Max Activating Token Index: 805

Text #8

Max Range: 2.6385. Min Range: -2.6385

Max Act: 2.3193. Min Act: -0.0000

Data Index: 294780 (C4 (Web Text))

Max Activating Token Index: 348

Text #9

Max Range: 2.6385. Min Range: -2.6385

Max Act: 2.3859. Min Act: -0.0000

Data Index: 1362313 (Python Code)

Max Activating Token Index: 113

Text #10

Max Range: 2.6385. Min Range: -2.6385

Max Act: 2.3382. Min Act: -0.0000

Data Index: 1214079 (C4 (Web Text))

Max Activating Token Index: 994

Text #11

Max Range: 2.6385. Min Range: -2.6385

Max Act: 2.0927. Min Act: -0.0000

Data Index: 1246086 (C4 (Web Text))

Max Activating Token Index: 616

Text #12

Max Range: 2.6385. Min Range: -2.6385

Max Act: 2.3363. Min Act: -0.0000

Data Index: 172970 (C4 (Web Text))

Max Activating Token Index: 874

Text #13

Max Range: 2.6385. Min Range: -2.6385

Max Act: 2.1860. Min Act: -0.0000

Data Index: 240547 (C4 (Web Text))

Max Activating Token Index: 949

Text #14

Max Range: 2.6385. Min Range: -2.6385

Max Act: 2.2033. Min Act: -0.0000

Data Index: 90803 (C4 (Web Text))

Max Activating Token Index: 1000

Text #15

Max Range: 2.6385. Min Range: -2.6385

Max Act: 2.2515. Min Act: -0.0000

Data Index: 875579 (C4 (Web Text))

Max Activating Token Index: 897

Text #16

Max Range: 2.6385. Min Range: -2.6385

Max Act: 2.1125. Min Act: -0.0000

Data Index: 14155 (C4 (Web Text))

Max Activating Token Index: 551

Text #17

Max Range: 2.6385. Min Range: -2.6385

Max Act: 2.0875. Min Act: -0.0000

Data Index: 840236 (C4 (Web Text))

Max Activating Token Index: 226

Text #18

Max Range: 2.6385. Min Range: -2.6385

Max Act: 2.0848. Min Act: -0.0000

Data Index: 1575239 (Python Code)

Max Activating Token Index: 348

Text #19

Max Range: 2.6385. Min Range: -2.6385

Max Act: 1.9549. Min Act: -0.0000

Data Index: 5902 (C4 (Web Text))

Max Activating Token Index: 736