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

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

Neuron 578 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 1.1968. Min Range: -1.1968

Max Act: 1.1384. Min Act: -0.0001

Data Index: 822233 (C4 (Web Text))

Max Activating Token Index: 603

Text #1

Max Range: 1.1968. Min Range: -1.1968

Max Act: 1.1695. Min Act: -0.0001

Data Index: 327849 (C4 (Web Text))

Max Activating Token Index: 737

Text #2

Max Range: 1.1968. Min Range: -1.1968

Max Act: 1.1528. Min Act: -0.0001

Data Index: 48516 (C4 (Web Text))

Max Activating Token Index: 897

Text #3

Max Range: 1.1968. Min Range: -1.1968

Max Act: 1.0027. Min Act: -0.0001

Data Index: 29640 (C4 (Web Text))

Max Activating Token Index: 774

Text #4

Max Range: 1.1968. Min Range: -1.1968

Max Act: 1.0705. Min Act: -0.0001

Data Index: 269692 (C4 (Web Text))

Max Activating Token Index: 742

Text #5

Max Range: 1.1968. Min Range: -1.1968

Max Act: 1.0492. Min Act: -0.0001

Data Index: 859940 (C4 (Web Text))

Max Activating Token Index: 247

Text #6

Max Range: 1.1968. Min Range: -1.1968

Max Act: 1.1968. Min Act: -0.0001

Data Index: 173914 (C4 (Web Text))

Max Activating Token Index: 907

Text #7

Max Range: 1.1968. Min Range: -1.1968

Max Act: 1.0899. Min Act: -0.0001

Data Index: 804461 (C4 (Web Text))

Max Activating Token Index: 437

Text #8

Max Range: 1.1968. Min Range: -1.1968

Max Act: 1.0815. Min Act: -0.0001

Data Index: 728053 (C4 (Web Text))

Max Activating Token Index: 68

Text #9

Max Range: 1.1968. Min Range: -1.1968

Max Act: 1.0482. Min Act: -0.0001

Data Index: 185093 (C4 (Web Text))

Max Activating Token Index: 224

Text #10

Max Range: 1.1968. Min Range: -1.1968

Max Act: 1.0815. Min Act: -0.0001

Data Index: 642897 (C4 (Web Text))

Max Activating Token Index: 535

Text #11

Max Range: 1.1968. Min Range: -1.1968

Max Act: 1.1212. Min Act: -0.0001

Data Index: 907844 (C4 (Web Text))

Max Activating Token Index: 795

Text #12

Max Range: 1.1968. Min Range: -1.1968

Max Act: 1.0167. Min Act: -0.0001

Data Index: 182615 (C4 (Web Text))

Max Activating Token Index: 172

Text #13

Max Range: 1.1968. Min Range: -1.1968

Max Act: 1.0390. Min Act: -0.0001

Data Index: 1102333 (C4 (Web Text))

Max Activating Token Index: 105

Text #14

Max Range: 1.1968. Min Range: -1.1968

Max Act: 1.0879. Min Act: -0.0001

Data Index: 1167928 (C4 (Web Text))

Max Activating Token Index: 160

Text #15

Max Range: 1.1968. Min Range: -1.1968

Max Act: 1.0446. Min Act: -0.0001

Data Index: 23132 (C4 (Web Text))

Max Activating Token Index: 110

Text #16

Max Range: 1.1968. Min Range: -1.1968

Max Act: 1.0386. Min Act: -0.0001

Data Index: 137561 (C4 (Web Text))

Max Activating Token Index: 527

Text #17

Max Range: 1.1968. Min Range: -1.1968

Max Act: 1.0069. Min Act: -0.0001

Data Index: 11518 (C4 (Web Text))

Max Activating Token Index: 496

Text #18

Max Range: 1.1968. Min Range: -1.1968

Max Act: 1.0432. Min Act: -0.0001

Data Index: 483541 (C4 (Web Text))

Max Activating Token Index: 886

Text #19

Max Range: 1.1968. Min Range: -1.1968

Max Act: 1.0819. Min Act: -0.0001

Data Index: 839042 (C4 (Web Text))

Max Activating Token Index: 90