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

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

Neuron 3207 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.3543. Min Range: -2.3543

Max Act: 2.3543. Min Act: -0.0000

Data Index: 364050 (C4 (Web Text))

Max Activating Token Index: 857

Text #1

Max Range: 2.3543. Min Range: -2.3543

Max Act: 1.9333. Min Act: -0.0000

Data Index: 1360821 (Python Code)

Max Activating Token Index: 68

Text #2

Max Range: 2.3543. Min Range: -2.3543

Max Act: 2.0683. Min Act: -0.0000

Data Index: 675791 (C4 (Web Text))

Max Activating Token Index: 140

Text #3

Max Range: 2.3543. Min Range: -2.3543

Max Act: 2.0673. Min Act: -0.0000

Data Index: 1003500 (C4 (Web Text))

Max Activating Token Index: 926

Text #4

Max Range: 2.3543. Min Range: -2.3543

Max Act: 2.0572. Min Act: -0.0000

Data Index: 1059089 (C4 (Web Text))

Max Activating Token Index: 376

Text #5

Max Range: 2.3543. Min Range: -2.3543

Max Act: 2.0559. Min Act: -0.0000

Data Index: 1163450 (C4 (Web Text))

Max Activating Token Index: 235

Text #6

Max Range: 2.3543. Min Range: -2.3543

Max Act: 2.0521. Min Act: -0.0000

Data Index: 769155 (C4 (Web Text))

Max Activating Token Index: 667

Text #7

Max Range: 2.3543. Min Range: -2.3543

Max Act: 1.9119. Min Act: -0.0000

Data Index: 1213241 (C4 (Web Text))

Max Activating Token Index: 912

Text #8

Max Range: 2.3543. Min Range: -2.3543

Max Act: 2.1327. Min Act: -0.0000

Data Index: 774545 (C4 (Web Text))

Max Activating Token Index: 128

Text #9

Max Range: 2.3543. Min Range: -2.3543

Max Act: 2.1155. Min Act: -0.0000

Data Index: 777682 (C4 (Web Text))

Max Activating Token Index: 932

Text #10

Max Range: 2.3543. Min Range: -2.3543

Max Act: 1.9982. Min Act: -0.0000

Data Index: 933431 (C4 (Web Text))

Max Activating Token Index: 23

Text #11

Max Range: 2.3543. Min Range: -2.3543

Max Act: 2.0063. Min Act: -0.0000

Data Index: 757633 (C4 (Web Text))

Max Activating Token Index: 994

Text #12

Max Range: 2.3543. Min Range: -2.3543

Max Act: 1.8867. Min Act: -0.0000

Data Index: 962158 (C4 (Web Text))

Max Activating Token Index: 265

Text #13

Max Range: 2.3543. Min Range: -2.3543

Max Act: 1.9600. Min Act: -0.0000

Data Index: 290719 (C4 (Web Text))

Max Activating Token Index: 589

Text #14

Max Range: 2.3543. Min Range: -2.3543

Max Act: 1.8380. Min Act: -0.0000

Data Index: 524782 (C4 (Web Text))

Max Activating Token Index: 512

Text #15

Max Range: 2.3543. Min Range: -2.3543

Max Act: 1.8156. Min Act: -0.0000

Data Index: 287592 (C4 (Web Text))

Max Activating Token Index: 881

Text #16

Max Range: 2.3543. Min Range: -2.3543

Max Act: 1.8949. Min Act: -0.0000

Data Index: 33306 (C4 (Web Text))

Max Activating Token Index: 32

Text #17

Max Range: 2.3543. Min Range: -2.3543

Max Act: 1.8698. Min Act: -0.0000

Data Index: 1006414 (C4 (Web Text))

Max Activating Token Index: 409

Text #18

Max Range: 2.3543. Min Range: -2.3543

Max Act: 1.8548. Min Act: -0.0000

Data Index: 98068 (C4 (Web Text))

Max Activating Token Index: 329

Text #19

Max Range: 2.3543. Min Range: -2.3543

Max Act: 1.8667. Min Act: -0.0000

Data Index: 216774 (C4 (Web Text))

Max Activating Token Index: 1004