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

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

Neuron 1149 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0492. Min Range: -1.0492

Max Act: 1.0492. Min Act: -0.0000

Data Index: 373541 (C4 (Web Text))

Max Activating Token Index: 1009

Text #1

Max Range: 1.0492. Min Range: -1.0492

Max Act: 0.7771. Min Act: 0.0000

Data Index: 595576 (C4 (Web Text))

Max Activating Token Index: 934

Text #2

Max Range: 1.0492. Min Range: -1.0492

Max Act: 0.7137. Min Act: -0.0000

Data Index: 527102 (C4 (Web Text))

Max Activating Token Index: 892

Text #3

Max Range: 1.0492. Min Range: -1.0492

Max Act: 0.7458. Min Act: -0.0000

Data Index: 111968 (C4 (Web Text))

Max Activating Token Index: 614

Text #4

Max Range: 1.0492. Min Range: -1.0492

Max Act: 0.7720. Min Act: -0.0000

Data Index: 1186091 (C4 (Web Text))

Max Activating Token Index: 461

Text #5

Max Range: 1.0492. Min Range: -1.0492

Max Act: 0.8136. Min Act: -0.0000

Data Index: 424104 (C4 (Web Text))

Max Activating Token Index: 359

Text #6

Max Range: 1.0492. Min Range: -1.0492

Max Act: 0.7126. Min Act: -0.0000

Data Index: 1349423 (C4 (Web Text))

Max Activating Token Index: 499

Text #7

Max Range: 1.0492. Min Range: -1.0492

Max Act: 0.7482. Min Act: -0.0000

Data Index: 975977 (C4 (Web Text))

Max Activating Token Index: 694

Text #8

Max Range: 1.0492. Min Range: -1.0492

Max Act: 0.7136. Min Act: -0.0000

Data Index: 910017 (C4 (Web Text))

Max Activating Token Index: 442

Text #9

Max Range: 1.0492. Min Range: -1.0492

Max Act: 0.6741. Min Act: -0.0000

Data Index: 1282700 (C4 (Web Text))

Max Activating Token Index: 50

Text #10

Max Range: 1.0492. Min Range: -1.0492

Max Act: 0.7191. Min Act: -0.0000

Data Index: 918365 (C4 (Web Text))

Max Activating Token Index: 64

Text #11

Max Range: 1.0492. Min Range: -1.0492

Max Act: 0.6986. Min Act: -0.0000

Data Index: 997151 (C4 (Web Text))

Max Activating Token Index: 397

Text #12

Max Range: 1.0492. Min Range: -1.0492

Max Act: 0.6944. Min Act: -0.0000

Data Index: 159888 (C4 (Web Text))

Max Activating Token Index: 1017

Text #13

Max Range: 1.0492. Min Range: -1.0492

Max Act: 0.6911. Min Act: 0.0000

Data Index: 770868 (C4 (Web Text))

Max Activating Token Index: 423

Text #14

Max Range: 1.0492. Min Range: -1.0492

Max Act: 0.6613. Min Act: -0.0000

Data Index: 1036360 (C4 (Web Text))

Max Activating Token Index: 23

Text #15

Max Range: 1.0492. Min Range: -1.0492

Max Act: 0.6608. Min Act: -0.0000

Data Index: 239935 (C4 (Web Text))

Max Activating Token Index: 47

Text #16

Max Range: 1.0492. Min Range: -1.0492

Max Act: 0.6420. Min Act: -0.0000

Data Index: 1071800 (C4 (Web Text))

Max Activating Token Index: 467

Text #17

Max Range: 1.0492. Min Range: -1.0492

Max Act: 0.6339. Min Act: -0.0000

Data Index: 1210291 (C4 (Web Text))

Max Activating Token Index: 511

Text #18

Max Range: 1.0492. Min Range: -1.0492

Max Act: 0.6569. Min Act: -0.0000

Data Index: 553716 (C4 (Web Text))

Max Activating Token Index: 655

Text #19

Max Range: 1.0492. Min Range: -1.0492

Max Act: 0.6308. Min Act: -0.0000

Data Index: 91647 (C4 (Web Text))

Max Activating Token Index: 630