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

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

Neuron 2061 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6122. Min Range: -0.6122

Max Act: 0.5600. Min Act: -0.0001

Data Index: 1187550 (C4 (Web Text))

Max Activating Token Index: 861

Text #1

Max Range: 0.6122. Min Range: -0.6122

Max Act: 0.5586. Min Act: -0.0001

Data Index: 235077 (C4 (Web Text))

Max Activating Token Index: 802

Text #2

Max Range: 0.6122. Min Range: -0.6122

Max Act: 0.5867. Min Act: -0.0001

Data Index: 390133 (C4 (Web Text))

Max Activating Token Index: 664

Text #3

Max Range: 0.6122. Min Range: -0.6122

Max Act: 0.4915. Min Act: -0.0001

Data Index: 1333583 (C4 (Web Text))

Max Activating Token Index: 834

Text #4

Max Range: 0.6122. Min Range: -0.6122

Max Act: 0.6122. Min Act: -0.0001

Data Index: 591266 (C4 (Web Text))

Max Activating Token Index: 82

Text #5

Max Range: 0.6122. Min Range: -0.6122

Max Act: 0.5128. Min Act: -0.0001

Data Index: 208377 (C4 (Web Text))

Max Activating Token Index: 40

Text #6

Max Range: 0.6122. Min Range: -0.6122

Max Act: 0.4967. Min Act: -0.0001

Data Index: 1096877 (C4 (Web Text))

Max Activating Token Index: 728

Text #7

Max Range: 0.6122. Min Range: -0.6122

Max Act: 0.5350. Min Act: -0.0001

Data Index: 366330 (C4 (Web Text))

Max Activating Token Index: 47

Text #8

Max Range: 0.6122. Min Range: -0.6122

Max Act: 0.5040. Min Act: -0.0001

Data Index: 1107714 (C4 (Web Text))

Max Activating Token Index: 14

Text #9

Max Range: 0.6122. Min Range: -0.6122

Max Act: 0.5194. Min Act: -0.0001

Data Index: 1272191 (C4 (Web Text))

Max Activating Token Index: 78

Text #10

Max Range: 0.6122. Min Range: -0.6122

Max Act: 0.5585. Min Act: -0.0001

Data Index: 1014052 (C4 (Web Text))

Max Activating Token Index: 857

Text #11

Max Range: 0.6122. Min Range: -0.6122

Max Act: 0.5175. Min Act: -0.0001

Data Index: 847671 (C4 (Web Text))

Max Activating Token Index: 52

Text #12

Max Range: 0.6122. Min Range: -0.6122

Max Act: 0.5256. Min Act: -0.0001

Data Index: 785939 (C4 (Web Text))

Max Activating Token Index: 348

Text #13

Max Range: 0.6122. Min Range: -0.6122

Max Act: 0.4595. Min Act: -0.0001

Data Index: 33149 (C4 (Web Text))

Max Activating Token Index: 735

Text #14

Max Range: 0.6122. Min Range: -0.6122

Max Act: 0.4725. Min Act: -0.0001

Data Index: 101350 (C4 (Web Text))

Max Activating Token Index: 373

Text #15

Max Range: 0.6122. Min Range: -0.6122

Max Act: 0.4869. Min Act: -0.0001

Data Index: 334709 (C4 (Web Text))

Max Activating Token Index: 986

Text #16

Max Range: 0.6122. Min Range: -0.6122

Max Act: 0.4560. Min Act: -0.0001

Data Index: 1136385 (C4 (Web Text))

Max Activating Token Index: 8

Text #17

Max Range: 0.6122. Min Range: -0.6122

Max Act: 0.4714. Min Act: -0.0001

Data Index: 184234 (C4 (Web Text))

Max Activating Token Index: 157

Text #18

Max Range: 0.6122. Min Range: -0.6122

Max Act: 0.5027. Min Act: -0.0001

Data Index: 697052 (C4 (Web Text))

Max Activating Token Index: 441

Text #19

Max Range: 0.6122. Min Range: -0.6122

Max Act: 0.4846. Min Act: -0.0001

Data Index: 1035123 (C4 (Web Text))

Max Activating Token Index: 925