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

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

Neuron 89 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0917. Min Range: -1.0917

Max Act: 1.0917. Min Act: -0.0000

Data Index: 736749 (C4 (Web Text))

Max Activating Token Index: 857

Text #1

Max Range: 1.0917. Min Range: -1.0917

Max Act: 0.8462. Min Act: -0.0000

Data Index: 139934 (C4 (Web Text))

Max Activating Token Index: 686

Text #2

Max Range: 1.0917. Min Range: -1.0917

Max Act: 0.8112. Min Act: -0.0000

Data Index: 462400 (C4 (Web Text))

Max Activating Token Index: 196

Text #3

Max Range: 1.0917. Min Range: -1.0917

Max Act: 0.8296. Min Act: -0.0001

Data Index: 831764 (C4 (Web Text))

Max Activating Token Index: 414

Text #4

Max Range: 1.0917. Min Range: -1.0917

Max Act: 0.8183. Min Act: -0.0000

Data Index: 1017009 (C4 (Web Text))

Max Activating Token Index: 620

Text #5

Max Range: 1.0917. Min Range: -1.0917

Max Act: 0.8869. Min Act: -0.0001

Data Index: 879031 (C4 (Web Text))

Max Activating Token Index: 629

Text #6

Max Range: 1.0917. Min Range: -1.0917

Max Act: 0.8339. Min Act: -0.0000

Data Index: 1241839 (C4 (Web Text))

Max Activating Token Index: 705

Text #7

Max Range: 1.0917. Min Range: -1.0917

Max Act: 0.8256. Min Act: -0.0000

Data Index: 678816 (C4 (Web Text))

Max Activating Token Index: 628

Text #8

Max Range: 1.0917. Min Range: -1.0917

Max Act: 0.8698. Min Act: -0.0000

Data Index: 42349 (C4 (Web Text))

Max Activating Token Index: 974

Text #9

Max Range: 1.0917. Min Range: -1.0917

Max Act: 0.8113. Min Act: -0.0000

Data Index: 979640 (C4 (Web Text))

Max Activating Token Index: 678

Text #10

Max Range: 1.0917. Min Range: -1.0917

Max Act: 0.7612. Min Act: -0.0001

Data Index: 1045551 (C4 (Web Text))

Max Activating Token Index: 595

Text #11

Max Range: 1.0917. Min Range: -1.0917

Max Act: 0.7183. Min Act: -0.0000

Data Index: 897508 (C4 (Web Text))

Max Activating Token Index: 614

Text #12

Max Range: 1.0917. Min Range: -1.0917

Max Act: 0.7480. Min Act: -0.0000

Data Index: 259466 (C4 (Web Text))

Max Activating Token Index: 359

Text #13

Max Range: 1.0917. Min Range: -1.0917

Max Act: 0.7151. Min Act: -0.0000

Data Index: 22310 (C4 (Web Text))

Max Activating Token Index: 973

Text #14

Max Range: 1.0917. Min Range: -1.0917

Max Act: 0.7062. Min Act: -0.0000

Data Index: 695915 (C4 (Web Text))

Max Activating Token Index: 331

Text #15

Max Range: 1.0917. Min Range: -1.0917

Max Act: 0.7169. Min Act: -0.0000

Data Index: 944512 (C4 (Web Text))

Max Activating Token Index: 113

Text #16

Max Range: 1.0917. Min Range: -1.0917

Max Act: 0.7193. Min Act: -0.0001

Data Index: 609205 (C4 (Web Text))

Max Activating Token Index: 481

Text #17

Max Range: 1.0917. Min Range: -1.0917

Max Act: 0.7210. Min Act: -0.0000

Data Index: 220512 (C4 (Web Text))

Max Activating Token Index: 598

Text #18

Max Range: 1.0917. Min Range: -1.0917

Max Act: 0.7128. Min Act: -0.0000

Data Index: 100191 (C4 (Web Text))

Max Activating Token Index: 501

Text #19

Max Range: 1.0917. Min Range: -1.0917

Max Act: 0.7297. Min Act: -0.0000

Data Index: 1219584 (C4 (Web Text))

Max Activating Token Index: 816