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

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

Neuron 3503 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.1866. Min Range: -1.1866

Max Act: 1.1866. Min Act: -0.0000

Data Index: 1028778 (C4 (Web Text))

Max Activating Token Index: 105

Text #1

Max Range: 1.1866. Min Range: -1.1866

Max Act: 1.0124. Min Act: -0.0000

Data Index: 1185827 (C4 (Web Text))

Max Activating Token Index: 171

Text #2

Max Range: 1.1866. Min Range: -1.1866

Max Act: 0.9293. Min Act: -0.0000

Data Index: 180518 (C4 (Web Text))

Max Activating Token Index: 723

Text #3

Max Range: 1.1866. Min Range: -1.1866

Max Act: 0.9842. Min Act: -0.0000

Data Index: 256569 (C4 (Web Text))

Max Activating Token Index: 750

Text #4

Max Range: 1.1866. Min Range: -1.1866

Max Act: 0.9335. Min Act: -0.0000

Data Index: 384616 (C4 (Web Text))

Max Activating Token Index: 183

Text #5

Max Range: 1.1866. Min Range: -1.1866

Max Act: 0.9832. Min Act: -0.0000

Data Index: 1010706 (C4 (Web Text))

Max Activating Token Index: 570

Text #6

Max Range: 1.1866. Min Range: -1.1866

Max Act: 0.9144. Min Act: -0.0000

Data Index: 860578 (C4 (Web Text))

Max Activating Token Index: 346

Text #7

Max Range: 1.1866. Min Range: -1.1866

Max Act: 0.9202. Min Act: -0.0000

Data Index: 874683 (C4 (Web Text))

Max Activating Token Index: 348

Text #8

Max Range: 1.1866. Min Range: -1.1866

Max Act: 0.8862. Min Act: 0.0000

Data Index: 1282478 (C4 (Web Text))

Max Activating Token Index: 940

Text #9

Max Range: 1.1866. Min Range: -1.1866

Max Act: 0.8744. Min Act: -0.0000

Data Index: 337705 (C4 (Web Text))

Max Activating Token Index: 496

Text #10

Max Range: 1.1866. Min Range: -1.1866

Max Act: 0.8635. Min Act: -0.0000

Data Index: 688380 (C4 (Web Text))

Max Activating Token Index: 58

Text #11

Max Range: 1.1866. Min Range: -1.1866

Max Act: 0.8490. Min Act: -0.0000

Data Index: 133709 (C4 (Web Text))

Max Activating Token Index: 980

Text #12

Max Range: 1.1866. Min Range: -1.1866

Max Act: 0.8239. Min Act: -0.0000

Data Index: 901428 (C4 (Web Text))

Max Activating Token Index: 287

Text #13

Max Range: 1.1866. Min Range: -1.1866

Max Act: 0.8675. Min Act: -0.0000

Data Index: 158475 (C4 (Web Text))

Max Activating Token Index: 937

Text #14

Max Range: 1.1866. Min Range: -1.1866

Max Act: 0.8204. Min Act: -0.0000

Data Index: 363740 (C4 (Web Text))

Max Activating Token Index: 236

Text #15

Max Range: 1.1866. Min Range: -1.1866

Max Act: 0.8042. Min Act: -0.0000

Data Index: 954881 (C4 (Web Text))

Max Activating Token Index: 896

Text #16

Max Range: 1.1866. Min Range: -1.1866

Max Act: 0.8455. Min Act: -0.0000

Data Index: 413441 (C4 (Web Text))

Max Activating Token Index: 764

Text #17

Max Range: 1.1866. Min Range: -1.1866

Max Act: 0.8691. Min Act: -0.0000

Data Index: 99639 (C4 (Web Text))

Max Activating Token Index: 189

Text #18

Max Range: 1.1866. Min Range: -1.1866

Max Act: 0.8401. Min Act: -0.0000

Data Index: 1245857 (C4 (Web Text))

Max Activating Token Index: 1019

Text #19

Max Range: 1.1866. Min Range: -1.1866

Max Act: 0.8111. Min Act: -0.0000

Data Index: 373762 (C4 (Web Text))

Max Activating Token Index: 102