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

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

Neuron 3458 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Click the toggle to see the full text!

Text #0

Max Range: 1.1043. Min Range: -1.1043

Max Act: 1.0953. Min Act: -0.0001

Data Index: 1181888 (C4 (Web Text))

Max Activating Token Index: 866

Text #1

Max Range: 1.1043. Min Range: -1.1043

Max Act: 1.0883. Min Act: -0.0001

Data Index: 125180 (C4 (Web Text))

Max Activating Token Index: 694

Text #2

Max Range: 1.1043. Min Range: -1.1043

Max Act: 1.1043. Min Act: -0.0001

Data Index: 466888 (C4 (Web Text))

Max Activating Token Index: 755

Text #3

Max Range: 1.1043. Min Range: -1.1043

Max Act: 1.0704. Min Act: -0.0001

Data Index: 1065447 (C4 (Web Text))

Max Activating Token Index: 678

Text #4

Max Range: 1.1043. Min Range: -1.1043

Max Act: 1.0677. Min Act: -0.0001

Data Index: 487167 (C4 (Web Text))

Max Activating Token Index: 646

Text #5

Max Range: 1.1043. Min Range: -1.1043

Max Act: 1.0668. Min Act: -0.0001

Data Index: 166505 (C4 (Web Text))

Max Activating Token Index: 886

Text #6

Max Range: 1.1043. Min Range: -1.1043

Max Act: 1.0456. Min Act: -0.0001

Data Index: 234928 (C4 (Web Text))

Max Activating Token Index: 771

Text #7

Max Range: 1.1043. Min Range: -1.1043

Max Act: 1.0443. Min Act: -0.0002

Data Index: 451648 (C4 (Web Text))

Max Activating Token Index: 796

Text #8

Max Range: 1.1043. Min Range: -1.1043

Max Act: 1.0526. Min Act: -0.0001

Data Index: 717197 (C4 (Web Text))

Max Activating Token Index: 740

Text #9

Max Range: 1.1043. Min Range: -1.1043

Max Act: 1.0501. Min Act: -0.0001

Data Index: 324675 (C4 (Web Text))

Max Activating Token Index: 613

Text #10

Max Range: 1.1043. Min Range: -1.1043

Max Act: 1.0312. Min Act: -0.0001

Data Index: 915570 (C4 (Web Text))

Max Activating Token Index: 840

Text #11

Max Range: 1.1043. Min Range: -1.1043

Max Act: 1.0398. Min Act: -0.0001

Data Index: 827923 (C4 (Web Text))

Max Activating Token Index: 731

Text #12

Max Range: 1.1043. Min Range: -1.1043

Max Act: 1.0124. Min Act: -0.0001

Data Index: 1069060 (C4 (Web Text))

Max Activating Token Index: 473

Text #13

Max Range: 1.1043. Min Range: -1.1043

Max Act: 1.0110. Min Act: -0.0001

Data Index: 947681 (C4 (Web Text))

Max Activating Token Index: 699

Text #14

Max Range: 1.1043. Min Range: -1.1043

Max Act: 1.0153. Min Act: -0.0001

Data Index: 45988 (C4 (Web Text))

Max Activating Token Index: 600

Text #15

Max Range: 1.1043. Min Range: -1.1043

Max Act: 1.0175. Min Act: -0.0001

Data Index: 464269 (C4 (Web Text))

Max Activating Token Index: 889

Text #16

Max Range: 1.1043. Min Range: -1.1043

Max Act: 1.0179. Min Act: -0.0001

Data Index: 1136383 (C4 (Web Text))

Max Activating Token Index: 20

Text #17

Max Range: 1.1043. Min Range: -1.1043

Max Act: 1.0243. Min Act: -0.0001

Data Index: 614391 (C4 (Web Text))

Max Activating Token Index: 782

Text #18

Max Range: 1.1043. Min Range: -1.1043

Max Act: 1.0063. Min Act: -0.0001

Data Index: 1016969 (C4 (Web Text))

Max Activating Token Index: 496

Text #19

Max Range: 1.1043. Min Range: -1.1043

Max Act: 1.0055. Min Act: -0.0001

Data Index: 369371 (C4 (Web Text))

Max Activating Token Index: 334