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

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

Neuron 3155 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: 1.4112. Min Range: -1.4112

Max Act: 1.4112. Min Act: -0.0000

Data Index: 746639 (C4 (Web Text))

Max Activating Token Index: 799

Text #1

Max Range: 1.4112. Min Range: -1.4112

Max Act: 1.0464. Min Act: -0.0000

Data Index: 1308969 (C4 (Web Text))

Max Activating Token Index: 778

Text #2

Max Range: 1.4112. Min Range: -1.4112

Max Act: 1.0309. Min Act: -0.0000

Data Index: 764041 (C4 (Web Text))

Max Activating Token Index: 841

Text #3

Max Range: 1.4112. Min Range: -1.4112

Max Act: 0.9368. Min Act: -0.0000

Data Index: 1158933 (C4 (Web Text))

Max Activating Token Index: 253

Text #4

Max Range: 1.4112. Min Range: -1.4112

Max Act: 0.9571. Min Act: -0.0000

Data Index: 444819 (C4 (Web Text))

Max Activating Token Index: 431

Text #5

Max Range: 1.4112. Min Range: -1.4112

Max Act: 0.8940. Min Act: -0.0000

Data Index: 1137313 (C4 (Web Text))

Max Activating Token Index: 516

Text #6

Max Range: 1.4112. Min Range: -1.4112

Max Act: 0.8808. Min Act: -0.0000

Data Index: 122394 (C4 (Web Text))

Max Activating Token Index: 230

Text #7

Max Range: 1.4112. Min Range: -1.4112

Max Act: 0.9144. Min Act: -0.0000

Data Index: 435390 (C4 (Web Text))

Max Activating Token Index: 867

Text #8

Max Range: 1.4112. Min Range: -1.4112

Max Act: 0.8710. Min Act: -0.0000

Data Index: 1357758 (C4 (Web Text))

Max Activating Token Index: 670

Text #9

Max Range: 1.4112. Min Range: -1.4112

Max Act: 0.8553. Min Act: -0.0000

Data Index: 670030 (C4 (Web Text))

Max Activating Token Index: 356

Text #10

Max Range: 1.4112. Min Range: -1.4112

Max Act: 0.9392. Min Act: -0.0000

Data Index: 69453 (C4 (Web Text))

Max Activating Token Index: 927

Text #11

Max Range: 1.4112. Min Range: -1.4112

Max Act: 0.8977. Min Act: -0.0000

Data Index: 368209 (C4 (Web Text))

Max Activating Token Index: 187

Text #12

Max Range: 1.4112. Min Range: -1.4112

Max Act: 0.8723. Min Act: -0.0000

Data Index: 291184 (C4 (Web Text))

Max Activating Token Index: 707

Text #13

Max Range: 1.4112. Min Range: -1.4112

Max Act: 0.8460. Min Act: -0.0000

Data Index: 1067310 (C4 (Web Text))

Max Activating Token Index: 58

Text #14

Max Range: 1.4112. Min Range: -1.4112

Max Act: 0.8446. Min Act: -0.0000

Data Index: 333867 (C4 (Web Text))

Max Activating Token Index: 985

Text #15

Max Range: 1.4112. Min Range: -1.4112

Max Act: 0.8326. Min Act: -0.0000

Data Index: 563320 (C4 (Web Text))

Max Activating Token Index: 617

Text #16

Max Range: 1.4112. Min Range: -1.4112

Max Act: 0.8779. Min Act: -0.0000

Data Index: 93801 (C4 (Web Text))

Max Activating Token Index: 1018

Text #17

Max Range: 1.4112. Min Range: -1.4112

Max Act: 0.8409. Min Act: -0.0000

Data Index: 761235 (C4 (Web Text))

Max Activating Token Index: 165

Text #18

Max Range: 1.4112. Min Range: -1.4112

Max Act: 0.8109. Min Act: -0.0000

Data Index: 1055780 (C4 (Web Text))

Max Activating Token Index: 170

Text #19

Max Range: 1.4112. Min Range: -1.4112

Max Act: 0.8166. Min Act: -0.0000

Data Index: 993366 (C4 (Web Text))

Max Activating Token Index: 698