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

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

Neuron 3039 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: 4.1113. Min Range: -4.1113

Max Act: 4.1113. Min Act: -0.0001

Data Index: 959257 (C4 (Web Text))

Max Activating Token Index: 26

Text #1

Max Range: 4.1113. Min Range: -4.1113

Max Act: 3.5435. Min Act: -0.0001

Data Index: 168378 (C4 (Web Text))

Max Activating Token Index: 849

Text #2

Max Range: 4.1113. Min Range: -4.1113

Max Act: 3.6910. Min Act: -0.0001

Data Index: 492279 (C4 (Web Text))

Max Activating Token Index: 33

Text #3

Max Range: 4.1113. Min Range: -4.1113

Max Act: 3.3514. Min Act: -0.0001

Data Index: 806369 (C4 (Web Text))

Max Activating Token Index: 358

Text #4

Max Range: 4.1113. Min Range: -4.1113

Max Act: 3.0851. Min Act: -0.0001

Data Index: 963616 (C4 (Web Text))

Max Activating Token Index: 275

Text #5

Max Range: 4.1113. Min Range: -4.1113

Max Act: 3.6838. Min Act: -0.0001

Data Index: 56165 (C4 (Web Text))

Max Activating Token Index: 34

Text #6

Max Range: 4.1113. Min Range: -4.1113

Max Act: 2.9751. Min Act: -0.0001

Data Index: 1145320 (C4 (Web Text))

Max Activating Token Index: 874

Text #7

Max Range: 4.1113. Min Range: -4.1113

Max Act: 3.2670. Min Act: -0.0001

Data Index: 1079164 (C4 (Web Text))

Max Activating Token Index: 119

Text #8

Max Range: 4.1113. Min Range: -4.1113

Max Act: 3.0845. Min Act: -0.0001

Data Index: 1109071 (C4 (Web Text))

Max Activating Token Index: 257

Text #9

Max Range: 4.1113. Min Range: -4.1113

Max Act: 3.3653. Min Act: -0.0001

Data Index: 424320 (C4 (Web Text))

Max Activating Token Index: 114

Text #10

Max Range: 4.1113. Min Range: -4.1113

Max Act: 3.1036. Min Act: -0.0001

Data Index: 80775 (C4 (Web Text))

Max Activating Token Index: 219

Text #11

Max Range: 4.1113. Min Range: -4.1113

Max Act: 2.8916. Min Act: -0.0000

Data Index: 1351725 (C4 (Web Text))

Max Activating Token Index: 636

Text #12

Max Range: 4.1113. Min Range: -4.1113

Max Act: 3.2537. Min Act: -0.0001

Data Index: 496594 (C4 (Web Text))

Max Activating Token Index: 40

Text #13

Max Range: 4.1113. Min Range: -4.1113

Max Act: 2.8961. Min Act: -0.0000

Data Index: 255465 (C4 (Web Text))

Max Activating Token Index: 277

Text #14

Max Range: 4.1113. Min Range: -4.1113

Max Act: 3.2658. Min Act: -0.0001

Data Index: 307865 (C4 (Web Text))

Max Activating Token Index: 799

Text #15

Max Range: 4.1113. Min Range: -4.1113

Max Act: 3.1030. Min Act: -0.0001

Data Index: 701607 (C4 (Web Text))

Max Activating Token Index: 247

Text #16

Max Range: 4.1113. Min Range: -4.1113

Max Act: 2.8610. Min Act: -0.0000

Data Index: 360409 (C4 (Web Text))

Max Activating Token Index: 1020

Text #17

Max Range: 4.1113. Min Range: -4.1113

Max Act: 2.8599. Min Act: -0.0001

Data Index: 1333273 (C4 (Web Text))

Max Activating Token Index: 58

Text #18

Max Range: 4.1113. Min Range: -4.1113

Max Act: 3.1162. Min Act: -0.0001

Data Index: 1114367 (C4 (Web Text))

Max Activating Token Index: 465

Text #19

Max Range: 4.1113. Min Range: -4.1113

Max Act: 3.1097. Min Act: -0.0001

Data Index: 260127 (C4 (Web Text))

Max Activating Token Index: 61