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

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

Neuron 3602 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0947. Min Range: -1.0947

Max Act: 1.0741. Min Act: -0.0001

Data Index: 1013470 (C4 (Web Text))

Max Activating Token Index: 495

Text #1

Max Range: 1.0947. Min Range: -1.0947

Max Act: 1.0947. Min Act: -0.0001

Data Index: 181091 (C4 (Web Text))

Max Activating Token Index: 85

Text #2

Max Range: 1.0947. Min Range: -1.0947

Max Act: 0.9955. Min Act: -0.0001

Data Index: 1222459 (C4 (Web Text))

Max Activating Token Index: 613

Text #3

Max Range: 1.0947. Min Range: -1.0947

Max Act: 0.9801. Min Act: -0.0001

Data Index: 226872 (C4 (Web Text))

Max Activating Token Index: 151

Text #4

Max Range: 1.0947. Min Range: -1.0947

Max Act: 0.9761. Min Act: -0.0001

Data Index: 479275 (C4 (Web Text))

Max Activating Token Index: 969

Text #5

Max Range: 1.0947. Min Range: -1.0947

Max Act: 0.9734. Min Act: -0.0001

Data Index: 393111 (C4 (Web Text))

Max Activating Token Index: 610

Text #6

Max Range: 1.0947. Min Range: -1.0947

Max Act: 1.0511. Min Act: -0.0001

Data Index: 374968 (C4 (Web Text))

Max Activating Token Index: 222

Text #7

Max Range: 1.0947. Min Range: -1.0947

Max Act: 1.0009. Min Act: -0.0001

Data Index: 583070 (C4 (Web Text))

Max Activating Token Index: 842

Text #8

Max Range: 1.0947. Min Range: -1.0947

Max Act: 0.9166. Min Act: -0.0001

Data Index: 360831 (C4 (Web Text))

Max Activating Token Index: 586

Text #9

Max Range: 1.0947. Min Range: -1.0947

Max Act: 0.9476. Min Act: -0.0001

Data Index: 1296553 (C4 (Web Text))

Max Activating Token Index: 889

Text #10

Max Range: 1.0947. Min Range: -1.0947

Max Act: 0.9669. Min Act: -0.0001

Data Index: 278503 (C4 (Web Text))

Max Activating Token Index: 531

Text #11

Max Range: 1.0947. Min Range: -1.0947

Max Act: 0.9714. Min Act: -0.0001

Data Index: 763339 (C4 (Web Text))

Max Activating Token Index: 198

Text #12

Max Range: 1.0947. Min Range: -1.0947

Max Act: 0.9165. Min Act: -0.0001

Data Index: 876034 (C4 (Web Text))

Max Activating Token Index: 672

Text #13

Max Range: 1.0947. Min Range: -1.0947

Max Act: 0.9616. Min Act: -0.0001

Data Index: 698631 (C4 (Web Text))

Max Activating Token Index: 169

Text #14

Max Range: 1.0947. Min Range: -1.0947

Max Act: 0.9574. Min Act: -0.0001

Data Index: 79207 (C4 (Web Text))

Max Activating Token Index: 1019

Text #15

Max Range: 1.0947. Min Range: -1.0947

Max Act: 0.9536. Min Act: -0.0001

Data Index: 1223426 (C4 (Web Text))

Max Activating Token Index: 966

Text #16

Max Range: 1.0947. Min Range: -1.0947

Max Act: 0.9450. Min Act: -0.0001

Data Index: 1337739 (C4 (Web Text))

Max Activating Token Index: 866

Text #17

Max Range: 1.0947. Min Range: -1.0947

Max Act: 0.9198. Min Act: -0.0001

Data Index: 976654 (C4 (Web Text))

Max Activating Token Index: 404

Text #18

Max Range: 1.0947. Min Range: -1.0947

Max Act: 0.9222. Min Act: -0.0001

Data Index: 556142 (C4 (Web Text))

Max Activating Token Index: 959

Text #19

Max Range: 1.0947. Min Range: -1.0947

Max Act: 0.9270. Min Act: -0.0001

Data Index: 769509 (C4 (Web Text))

Max Activating Token Index: 624