Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 3175 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 4.8257. Min Range: -4.8257

Max Act: 4.8257. Min Act: -0.0000

Data Index: 435453 (C4 (Web Text))

Max Activating Token Index: 56

Text #1

Max Range: 4.8257. Min Range: -4.8257

Max Act: 3.9779. Min Act: -0.0000

Data Index: 290309 (C4 (Web Text))

Max Activating Token Index: 8

Text #2

Max Range: 4.8257. Min Range: -4.8257

Max Act: 3.6988. Min Act: -0.0000

Data Index: 1007175 (C4 (Web Text))

Max Activating Token Index: 97

Text #3

Max Range: 4.8257. Min Range: -4.8257

Max Act: 3.5743. Min Act: -0.0000

Data Index: 926325 (C4 (Web Text))

Max Activating Token Index: 113

Text #4

Max Range: 4.8257. Min Range: -4.8257

Max Act: 3.7166. Min Act: -0.0000

Data Index: 440759 (C4 (Web Text))

Max Activating Token Index: 338

Text #5

Max Range: 4.8257. Min Range: -4.8257

Max Act: 3.0763. Min Act: -0.0000

Data Index: 1261829 (C4 (Web Text))

Max Activating Token Index: 345

Text #6

Max Range: 4.8257. Min Range: -4.8257

Max Act: 3.1991. Min Act: -0.0000

Data Index: 1182574 (C4 (Web Text))

Max Activating Token Index: 318

Text #7

Max Range: 4.8257. Min Range: -4.8257

Max Act: 3.1778. Min Act: -0.0000

Data Index: 698228 (C4 (Web Text))

Max Activating Token Index: 474

Text #8

Max Range: 4.8257. Min Range: -4.8257

Max Act: 3.4408. Min Act: -0.0000

Data Index: 338367 (C4 (Web Text))

Max Activating Token Index: 462

Text #9

Max Range: 4.8257. Min Range: -4.8257

Max Act: 3.0914. Min Act: -0.0000

Data Index: 153254 (C4 (Web Text))

Max Activating Token Index: 98

Text #10

Max Range: 4.8257. Min Range: -4.8257

Max Act: 3.1008. Min Act: -0.0000

Data Index: 48460 (C4 (Web Text))

Max Activating Token Index: 222

Text #11

Max Range: 4.8257. Min Range: -4.8257

Max Act: 3.3112. Min Act: -0.0000

Data Index: 1093507 (C4 (Web Text))

Max Activating Token Index: 191

Text #12

Max Range: 4.8257. Min Range: -4.8257

Max Act: 3.0886. Min Act: -0.0000

Data Index: 1314605 (C4 (Web Text))

Max Activating Token Index: 753

Text #13

Max Range: 4.8257. Min Range: -4.8257

Max Act: 3.0990. Min Act: -0.0000

Data Index: 814753 (C4 (Web Text))

Max Activating Token Index: 79

Text #14

Max Range: 4.8257. Min Range: -4.8257

Max Act: 3.1206. Min Act: -0.0000

Data Index: 119823 (C4 (Web Text))

Max Activating Token Index: 267

Text #15

Max Range: 4.8257. Min Range: -4.8257

Max Act: 3.0048. Min Act: -0.0000

Data Index: 720003 (C4 (Web Text))

Max Activating Token Index: 136

Text #16

Max Range: 4.8257. Min Range: -4.8257

Max Act: 2.8637. Min Act: -0.0000

Data Index: 698792 (C4 (Web Text))

Max Activating Token Index: 305

Text #17

Max Range: 4.8257. Min Range: -4.8257

Max Act: 2.4374. Min Act: -0.0000

Data Index: 349608 (C4 (Web Text))

Max Activating Token Index: 205

Text #18

Max Range: 4.8257. Min Range: -4.8257

Max Act: 2.9698. Min Act: -0.0000

Data Index: 751986 (C4 (Web Text))

Max Activating Token Index: 122

Text #19

Max Range: 4.8257. Min Range: -4.8257

Max Act: 2.8034. Min Act: -0.0000

Data Index: 1227832 (C4 (Web Text))

Max Activating Token Index: 413