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

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

Neuron 1885 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: 1.5852. Min Range: -1.5852

Max Act: 1.5852. Min Act: -0.0000

Data Index: 1051234 (C4 (Web Text))

Max Activating Token Index: 736

Text #1

Max Range: 1.5852. Min Range: -1.5852

Max Act: 1.2179. Min Act: -0.0000

Data Index: 126345 (C4 (Web Text))

Max Activating Token Index: 885

Text #2

Max Range: 1.5852. Min Range: -1.5852

Max Act: 1.2244. Min Act: -0.0000

Data Index: 414004 (C4 (Web Text))

Max Activating Token Index: 752

Text #3

Max Range: 1.5852. Min Range: -1.5852

Max Act: 1.1085. Min Act: -0.0000

Data Index: 140310 (C4 (Web Text))

Max Activating Token Index: 1000

Text #4

Max Range: 1.5852. Min Range: -1.5852

Max Act: 1.0443. Min Act: -0.0000

Data Index: 815919 (C4 (Web Text))

Max Activating Token Index: 1015

Text #5

Max Range: 1.5852. Min Range: -1.5852

Max Act: 1.0384. Min Act: -0.0000

Data Index: 1215343 (C4 (Web Text))

Max Activating Token Index: 54

Text #6

Max Range: 1.5852. Min Range: -1.5852

Max Act: 1.0109. Min Act: -0.0000

Data Index: 554563 (C4 (Web Text))

Max Activating Token Index: 959

Text #7

Max Range: 1.5852. Min Range: -1.5852

Max Act: 1.0312. Min Act: -0.0000

Data Index: 996129 (C4 (Web Text))

Max Activating Token Index: 439

Text #8

Max Range: 1.5852. Min Range: -1.5852

Max Act: 1.0229. Min Act: -0.0000

Data Index: 932395 (C4 (Web Text))

Max Activating Token Index: 560

Text #9

Max Range: 1.5852. Min Range: -1.5852

Max Act: 1.0112. Min Act: -0.0000

Data Index: 63506 (C4 (Web Text))

Max Activating Token Index: 991

Text #10

Max Range: 1.5852. Min Range: -1.5852

Max Act: 0.9324. Min Act: -0.0000

Data Index: 370065 (C4 (Web Text))

Max Activating Token Index: 24

Text #11

Max Range: 1.5852. Min Range: -1.5852

Max Act: 0.9096. Min Act: -0.0000

Data Index: 259811 (C4 (Web Text))

Max Activating Token Index: 55

Text #12

Max Range: 1.5852. Min Range: -1.5852

Max Act: 0.9492. Min Act: -0.0000

Data Index: 1359595 (C4 (Web Text))

Max Activating Token Index: 537

Text #13

Max Range: 1.5852. Min Range: -1.5852

Max Act: 0.9209. Min Act: -0.0000

Data Index: 968758 (C4 (Web Text))

Max Activating Token Index: 375

Text #14

Max Range: 1.5852. Min Range: -1.5852

Max Act: 0.9760. Min Act: -0.0000

Data Index: 651177 (C4 (Web Text))

Max Activating Token Index: 954

Text #15

Max Range: 1.5852. Min Range: -1.5852

Max Act: 0.9491. Min Act: -0.0000

Data Index: 464612 (C4 (Web Text))

Max Activating Token Index: 989

Text #16

Max Range: 1.5852. Min Range: -1.5852

Max Act: 0.9201. Min Act: -0.0000

Data Index: 632889 (C4 (Web Text))

Max Activating Token Index: 96

Text #17

Max Range: 1.5852. Min Range: -1.5852

Max Act: 0.9482. Min Act: -0.0000

Data Index: 504270 (C4 (Web Text))

Max Activating Token Index: 621

Text #18

Max Range: 1.5852. Min Range: -1.5852

Max Act: 0.8601. Min Act: -0.0000

Data Index: 923640 (C4 (Web Text))

Max Activating Token Index: 711

Text #19

Max Range: 1.5852. Min Range: -1.5852

Max Act: 0.9357. Min Act: -0.0000

Data Index: 797990 (C4 (Web Text))

Max Activating Token Index: 407