Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 3114 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.5298. Min Range: -0.5298

Max Act: 0.5298. Min Act: -0.0001

Data Index: 1348523 (C4 (Web Text))

Max Activating Token Index: 630

Text #1

Max Range: 0.5298. Min Range: -0.5298

Max Act: 0.5081. Min Act: -0.0000

Data Index: 964532 (C4 (Web Text))

Max Activating Token Index: 598

Text #2

Max Range: 0.5298. Min Range: -0.5298

Max Act: 0.5169. Min Act: -0.0000

Data Index: 714563 (C4 (Web Text))

Max Activating Token Index: 461

Text #3

Max Range: 0.5298. Min Range: -0.5298

Max Act: 0.5075. Min Act: -0.0001

Data Index: 529979 (C4 (Web Text))

Max Activating Token Index: 93

Text #4

Max Range: 0.5298. Min Range: -0.5298

Max Act: 0.4906. Min Act: -0.0000

Data Index: 23194 (C4 (Web Text))

Max Activating Token Index: 840

Text #5

Max Range: 0.5298. Min Range: -0.5298

Max Act: 0.4560. Min Act: -0.0001

Data Index: 964941 (C4 (Web Text))

Max Activating Token Index: 836

Text #6

Max Range: 0.5298. Min Range: -0.5298

Max Act: 0.4862. Min Act: -0.0001

Data Index: 1059025 (C4 (Web Text))

Max Activating Token Index: 671

Text #7

Max Range: 0.5298. Min Range: -0.5298

Max Act: 0.4682. Min Act: -0.0000

Data Index: 888565 (C4 (Web Text))

Max Activating Token Index: 761

Text #8

Max Range: 0.5298. Min Range: -0.5298

Max Act: 0.4869. Min Act: -0.0000

Data Index: 44925 (C4 (Web Text))

Max Activating Token Index: 970

Text #9

Max Range: 0.5298. Min Range: -0.5298

Max Act: 0.4401. Min Act: -0.0001

Data Index: 118696 (C4 (Web Text))

Max Activating Token Index: 896

Text #10

Max Range: 0.5298. Min Range: -0.5298

Max Act: 0.4613. Min Act: -0.0000

Data Index: 771556 (C4 (Web Text))

Max Activating Token Index: 837

Text #11

Max Range: 0.5298. Min Range: -0.5298

Max Act: 0.4371. Min Act: -0.0001

Data Index: 148162 (C4 (Web Text))

Max Activating Token Index: 608

Text #12

Max Range: 0.5298. Min Range: -0.5298

Max Act: 0.4634. Min Act: -0.0000

Data Index: 337263 (C4 (Web Text))

Max Activating Token Index: 653

Text #13

Max Range: 0.5298. Min Range: -0.5298

Max Act: 0.4615. Min Act: -0.0001

Data Index: 725998 (C4 (Web Text))

Max Activating Token Index: 543

Text #14

Max Range: 0.5298. Min Range: -0.5298

Max Act: 0.4240. Min Act: -0.0000

Data Index: 33814 (C4 (Web Text))

Max Activating Token Index: 937

Text #15

Max Range: 0.5298. Min Range: -0.5298

Max Act: 0.4208. Min Act: -0.0001

Data Index: 1062286 (C4 (Web Text))

Max Activating Token Index: 833

Text #16

Max Range: 0.5298. Min Range: -0.5298

Max Act: 0.3956. Min Act: -0.0000

Data Index: 841281 (C4 (Web Text))

Max Activating Token Index: 600

Text #17

Max Range: 0.5298. Min Range: -0.5298

Max Act: 0.3992. Min Act: -0.0000

Data Index: 127859 (C4 (Web Text))

Max Activating Token Index: 1019

Text #18

Max Range: 0.5298. Min Range: -0.5298

Max Act: 0.4198. Min Act: -0.0001

Data Index: 927230 (C4 (Web Text))

Max Activating Token Index: 944

Text #19

Max Range: 0.5298. Min Range: -0.5298

Max Act: 0.3994. Min Act: -0.0000

Data Index: 39697 (C4 (Web Text))

Max Activating Token Index: 905