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

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

Neuron 5096 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.1188. Min Range: -1.1188

Max Act: 1.1188. Min Act: -0.0000

Data Index: 1287939 (C4 (Web Text))

Max Activating Token Index: 301

Text #1

Max Range: 1.1188. Min Range: -1.1188

Max Act: 1.0926. Min Act: -0.0000

Data Index: 864879 (C4 (Web Text))

Max Activating Token Index: 366

Text #2

Max Range: 1.1188. Min Range: -1.1188

Max Act: 0.9125. Min Act: -0.0000

Data Index: 66520 (C4 (Web Text))

Max Activating Token Index: 820

Text #3

Max Range: 1.1188. Min Range: -1.1188

Max Act: 1.1084. Min Act: -0.0000

Data Index: 415937 (C4 (Web Text))

Max Activating Token Index: 438

Text #4

Max Range: 1.1188. Min Range: -1.1188

Max Act: 0.8404. Min Act: -0.0000

Data Index: 814948 (C4 (Web Text))

Max Activating Token Index: 334

Text #5

Max Range: 1.1188. Min Range: -1.1188

Max Act: 0.6953. Min Act: -0.0000

Data Index: 266218 (C4 (Web Text))

Max Activating Token Index: 78

Text #6

Max Range: 1.1188. Min Range: -1.1188

Max Act: 0.6638. Min Act: -0.0000

Data Index: 530367 (C4 (Web Text))

Max Activating Token Index: 31

Text #7

Max Range: 1.1188. Min Range: -1.1188

Max Act: 0.7817. Min Act: -0.0000

Data Index: 569052 (C4 (Web Text))

Max Activating Token Index: 285

Text #8

Max Range: 1.1188. Min Range: -1.1188

Max Act: 0.7040. Min Act: -0.0000

Data Index: 1034592 (C4 (Web Text))

Max Activating Token Index: 729

Text #9

Max Range: 1.1188. Min Range: -1.1188

Max Act: 0.5798. Min Act: -0.0000

Data Index: 895605 (C4 (Web Text))

Max Activating Token Index: 323

Text #10

Max Range: 1.1188. Min Range: -1.1188

Max Act: 0.5823. Min Act: -0.0000

Data Index: 1324704 (C4 (Web Text))

Max Activating Token Index: 577

Text #11

Max Range: 1.1188. Min Range: -1.1188

Max Act: 0.6305. Min Act: -0.0000

Data Index: 882996 (C4 (Web Text))

Max Activating Token Index: 186

Text #12

Max Range: 1.1188. Min Range: -1.1188

Max Act: 0.5053. Min Act: -0.0000

Data Index: 307724 (C4 (Web Text))

Max Activating Token Index: 150

Text #13

Max Range: 1.1188. Min Range: -1.1188

Max Act: 0.5553. Min Act: -0.0000

Data Index: 1313082 (C4 (Web Text))

Max Activating Token Index: 292

Text #14

Max Range: 1.1188. Min Range: -1.1188

Max Act: 0.6291. Min Act: -0.0000

Data Index: 1170254 (C4 (Web Text))

Max Activating Token Index: 289

Text #15

Max Range: 1.1188. Min Range: -1.1188

Max Act: 0.5264. Min Act: -0.0000

Data Index: 707211 (C4 (Web Text))

Max Activating Token Index: 700

Text #16

Max Range: 1.1188. Min Range: -1.1188

Max Act: 0.4612. Min Act: -0.0000

Data Index: 897171 (C4 (Web Text))

Max Activating Token Index: 221

Text #17

Max Range: 1.1188. Min Range: -1.1188

Max Act: 0.4153. Min Act: -0.0000

Data Index: 749863 (C4 (Web Text))

Max Activating Token Index: 732

Text #18

Max Range: 1.1188. Min Range: -1.1188

Max Act: 0.4724. Min Act: -0.0000

Data Index: 325779 (C4 (Web Text))

Max Activating Token Index: 219

Text #19

Max Range: 1.1188. Min Range: -1.1188

Max Act: 0.4796. Min Act: -0.0000

Data Index: 1394824 (Python Code)

Max Activating Token Index: 233