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

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

Neuron 4065 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.4144. Min Range: -2.4144

Max Act: 2.2551. Min Act: -0.0000

Data Index: 601967 (C4 (Web Text))

Max Activating Token Index: 673

Text #1

Max Range: 2.4144. Min Range: -2.4144

Max Act: 2.4144. Min Act: -0.0000

Data Index: 1464793 (Python Code)

Max Activating Token Index: 758

Text #2

Max Range: 2.4144. Min Range: -2.4144

Max Act: 2.2869. Min Act: -0.0000

Data Index: 304664 (C4 (Web Text))

Max Activating Token Index: 550

Text #3

Max Range: 2.4144. Min Range: -2.4144

Max Act: 2.0652. Min Act: -0.0000

Data Index: 75324 (C4 (Web Text))

Max Activating Token Index: 99

Text #4

Max Range: 2.4144. Min Range: -2.4144

Max Act: 2.0316. Min Act: -0.0000

Data Index: 213315 (C4 (Web Text))

Max Activating Token Index: 970

Text #5

Max Range: 2.4144. Min Range: -2.4144

Max Act: 2.0219. Min Act: -0.0000

Data Index: 749865 (C4 (Web Text))

Max Activating Token Index: 926

Text #6

Max Range: 2.4144. Min Range: -2.4144

Max Act: 1.9979. Min Act: -0.0000

Data Index: 1496461 (Python Code)

Max Activating Token Index: 315

Text #7

Max Range: 2.4144. Min Range: -2.4144

Max Act: 1.8556. Min Act: -0.0000

Data Index: 1206322 (C4 (Web Text))

Max Activating Token Index: 651

Text #8

Max Range: 2.4144. Min Range: -2.4144

Max Act: 1.9061. Min Act: -0.0000

Data Index: 939930 (C4 (Web Text))

Max Activating Token Index: 86

Text #9

Max Range: 2.4144. Min Range: -2.4144

Max Act: 1.7935. Min Act: -0.0000

Data Index: 1295161 (C4 (Web Text))

Max Activating Token Index: 140

Text #10

Max Range: 2.4144. Min Range: -2.4144

Max Act: 1.7945. Min Act: -0.0000

Data Index: 1080805 (C4 (Web Text))

Max Activating Token Index: 373

Text #11

Max Range: 2.4144. Min Range: -2.4144

Max Act: 1.7799. Min Act: -0.0000

Data Index: 866683 (C4 (Web Text))

Max Activating Token Index: 722

Text #12

Max Range: 2.4144. Min Range: -2.4144

Max Act: 1.7805. Min Act: -0.0000

Data Index: 432902 (C4 (Web Text))

Max Activating Token Index: 121

Text #13

Max Range: 2.4144. Min Range: -2.4144

Max Act: 1.7295. Min Act: -0.0000

Data Index: 1027765 (C4 (Web Text))

Max Activating Token Index: 654

Text #14

Max Range: 2.4144. Min Range: -2.4144

Max Act: 1.6285. Min Act: -0.0000

Data Index: 23933 (C4 (Web Text))

Max Activating Token Index: 881

Text #15

Max Range: 2.4144. Min Range: -2.4144

Max Act: 1.6977. Min Act: -0.0000

Data Index: 73501 (C4 (Web Text))

Max Activating Token Index: 359

Text #16

Max Range: 2.4144. Min Range: -2.4144

Max Act: 1.6099. Min Act: -0.0000

Data Index: 425662 (C4 (Web Text))

Max Activating Token Index: 821

Text #17

Max Range: 2.4144. Min Range: -2.4144

Max Act: 1.6873. Min Act: -0.0000

Data Index: 23902 (C4 (Web Text))

Max Activating Token Index: 133

Text #18

Max Range: 2.4144. Min Range: -2.4144

Max Act: 1.6496. Min Act: -0.0000

Data Index: 1265598 (C4 (Web Text))

Max Activating Token Index: 529

Text #19

Max Range: 2.4144. Min Range: -2.4144

Max Act: 1.6444. Min Act: -0.0000

Data Index: 39159 (C4 (Web Text))

Max Activating Token Index: 704