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

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

Neuron 5877 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.0146. Min Range: -4.0146

Max Act: 4.0146. Min Act: -0.0000

Data Index: 1026982 (C4 (Web Text))

Max Activating Token Index: 792

Text #1

Max Range: 4.0146. Min Range: -4.0146

Max Act: 3.1897. Min Act: -0.0000

Data Index: 900415 (C4 (Web Text))

Max Activating Token Index: 179

Text #2

Max Range: 4.0146. Min Range: -4.0146

Max Act: 3.4268. Min Act: -0.0000

Data Index: 782925 (C4 (Web Text))

Max Activating Token Index: 879

Text #3

Max Range: 4.0146. Min Range: -4.0146

Max Act: 3.1225. Min Act: -0.0000

Data Index: 1227608 (C4 (Web Text))

Max Activating Token Index: 466

Text #4

Max Range: 4.0146. Min Range: -4.0146

Max Act: 3.2412. Min Act: -0.0000

Data Index: 817027 (C4 (Web Text))

Max Activating Token Index: 749

Text #5

Max Range: 4.0146. Min Range: -4.0146

Max Act: 3.1157. Min Act: -0.0000

Data Index: 698775 (C4 (Web Text))

Max Activating Token Index: 690

Text #6

Max Range: 4.0146. Min Range: -4.0146

Max Act: 3.0593. Min Act: -0.0000

Data Index: 28245 (C4 (Web Text))

Max Activating Token Index: 465

Text #7

Max Range: 4.0146. Min Range: -4.0146

Max Act: 2.9975. Min Act: -0.0000

Data Index: 908905 (C4 (Web Text))

Max Activating Token Index: 490

Text #8

Max Range: 4.0146. Min Range: -4.0146

Max Act: 3.1239. Min Act: -0.0000

Data Index: 310242 (C4 (Web Text))

Max Activating Token Index: 931

Text #9

Max Range: 4.0146. Min Range: -4.0146

Max Act: 3.1214. Min Act: -0.0000

Data Index: 77722 (C4 (Web Text))

Max Activating Token Index: 918

Text #10

Max Range: 4.0146. Min Range: -4.0146

Max Act: 2.9555. Min Act: -0.0000

Data Index: 613930 (C4 (Web Text))

Max Activating Token Index: 24

Text #11

Max Range: 4.0146. Min Range: -4.0146

Max Act: 3.0274. Min Act: -0.0000

Data Index: 469995 (C4 (Web Text))

Max Activating Token Index: 226

Text #12

Max Range: 4.0146. Min Range: -4.0146

Max Act: 3.1823. Min Act: -0.0000

Data Index: 449671 (C4 (Web Text))

Max Activating Token Index: 643

Text #13

Max Range: 4.0146. Min Range: -4.0146

Max Act: 3.0176. Min Act: -0.0000

Data Index: 109248 (C4 (Web Text))

Max Activating Token Index: 492

Text #14

Max Range: 4.0146. Min Range: -4.0146

Max Act: 2.8519. Min Act: -0.0000

Data Index: 1304068 (C4 (Web Text))

Max Activating Token Index: 609

Text #15

Max Range: 4.0146. Min Range: -4.0146

Max Act: 3.3574. Min Act: -0.0000

Data Index: 64510 (C4 (Web Text))

Max Activating Token Index: 240

Text #16

Max Range: 4.0146. Min Range: -4.0146

Max Act: 2.7858. Min Act: -0.0000

Data Index: 1014859 (C4 (Web Text))

Max Activating Token Index: 936

Text #17

Max Range: 4.0146. Min Range: -4.0146

Max Act: 2.7924. Min Act: -0.0000

Data Index: 610701 (C4 (Web Text))

Max Activating Token Index: 41

Text #18

Max Range: 4.0146. Min Range: -4.0146

Max Act: 2.7891. Min Act: -0.0000

Data Index: 1177366 (C4 (Web Text))

Max Activating Token Index: 31

Text #19

Max Range: 4.0146. Min Range: -4.0146

Max Act: 3.0493. Min Act: -0.0000

Data Index: 1163754 (C4 (Web Text))

Max Activating Token Index: 696