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

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

Neuron 799 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: 1.6091. Min Range: -1.6091

Max Act: 1.6091. Min Act: -0.0000

Data Index: 649958 (C4 (Web Text))

Max Activating Token Index: 463

Text #1

Max Range: 1.6091. Min Range: -1.6091

Max Act: 1.4870. Min Act: -0.0000

Data Index: 1007257 (C4 (Web Text))

Max Activating Token Index: 922

Text #2

Max Range: 1.6091. Min Range: -1.6091

Max Act: 1.3301. Min Act: -0.0000

Data Index: 209249 (C4 (Web Text))

Max Activating Token Index: 301

Text #3

Max Range: 1.6091. Min Range: -1.6091

Max Act: 1.3095. Min Act: -0.0000

Data Index: 50194 (C4 (Web Text))

Max Activating Token Index: 756

Text #4

Max Range: 1.6091. Min Range: -1.6091

Max Act: 1.1466. Min Act: -0.0000

Data Index: 576636 (C4 (Web Text))

Max Activating Token Index: 73

Text #5

Max Range: 1.6091. Min Range: -1.6091

Max Act: 1.1579. Min Act: -0.0000

Data Index: 315903 (C4 (Web Text))

Max Activating Token Index: 237

Text #6

Max Range: 1.6091. Min Range: -1.6091

Max Act: 1.1239. Min Act: -0.0000

Data Index: 280944 (C4 (Web Text))

Max Activating Token Index: 809

Text #7

Max Range: 1.6091. Min Range: -1.6091

Max Act: 1.0527. Min Act: -0.0000

Data Index: 1090701 (C4 (Web Text))

Max Activating Token Index: 203

Text #8

Max Range: 1.6091. Min Range: -1.6091

Max Act: 1.0632. Min Act: -0.0000

Data Index: 1086628 (C4 (Web Text))

Max Activating Token Index: 112

Text #9

Max Range: 1.6091. Min Range: -1.6091

Max Act: 1.0428. Min Act: -0.0000

Data Index: 143093 (C4 (Web Text))

Max Activating Token Index: 244

Text #10

Max Range: 1.6091. Min Range: -1.6091

Max Act: 1.0091. Min Act: -0.0000

Data Index: 1022326 (C4 (Web Text))

Max Activating Token Index: 660

Text #11

Max Range: 1.6091. Min Range: -1.6091

Max Act: 1.0436. Min Act: -0.0000

Data Index: 1252417 (C4 (Web Text))

Max Activating Token Index: 130

Text #12

Max Range: 1.6091. Min Range: -1.6091

Max Act: 1.0057. Min Act: -0.0000

Data Index: 1186191 (C4 (Web Text))

Max Activating Token Index: 605

Text #13

Max Range: 1.6091. Min Range: -1.6091

Max Act: 0.9865. Min Act: -0.0000

Data Index: 408179 (C4 (Web Text))

Max Activating Token Index: 594

Text #14

Max Range: 1.6091. Min Range: -1.6091

Max Act: 0.9745. Min Act: -0.0000

Data Index: 808394 (C4 (Web Text))

Max Activating Token Index: 647

Text #15

Max Range: 1.6091. Min Range: -1.6091

Max Act: 1.0020. Min Act: -0.0000

Data Index: 683316 (C4 (Web Text))

Max Activating Token Index: 805

Text #16

Max Range: 1.6091. Min Range: -1.6091

Max Act: 0.9703. Min Act: -0.0000

Data Index: 1192973 (C4 (Web Text))

Max Activating Token Index: 1022

Text #17

Max Range: 1.6091. Min Range: -1.6091

Max Act: 0.9842. Min Act: -0.0000

Data Index: 706100 (C4 (Web Text))

Max Activating Token Index: 516

Text #18

Max Range: 1.6091. Min Range: -1.6091

Max Act: 0.9984. Min Act: -0.0000

Data Index: 80873 (C4 (Web Text))

Max Activating Token Index: 624

Text #19

Max Range: 1.6091. Min Range: -1.6091

Max Act: 0.9716. Min Act: -0.0000

Data Index: 660396 (C4 (Web Text))

Max Activating Token Index: 306