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

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

Neuron 3464 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: 0.5245. Min Range: -0.5245

Max Act: 0.5245. Min Act: -0.0000

Data Index: 346689 (C4 (Web Text))

Max Activating Token Index: 15

Text #1

Max Range: 0.5245. Min Range: -0.5245

Max Act: 0.4869. Min Act: -0.0000

Data Index: 140072 (C4 (Web Text))

Max Activating Token Index: 611

Text #2

Max Range: 0.5245. Min Range: -0.5245

Max Act: 0.4854. Min Act: -0.0001

Data Index: 224869 (C4 (Web Text))

Max Activating Token Index: 422

Text #3

Max Range: 0.5245. Min Range: -0.5245

Max Act: 0.4600. Min Act: -0.0001

Data Index: 114956 (C4 (Web Text))

Max Activating Token Index: 553

Text #4

Max Range: 0.5245. Min Range: -0.5245

Max Act: 0.4488. Min Act: -0.0001

Data Index: 1118438 (C4 (Web Text))

Max Activating Token Index: 635

Text #5

Max Range: 0.5245. Min Range: -0.5245

Max Act: 0.4788. Min Act: -0.0000

Data Index: 63216 (C4 (Web Text))

Max Activating Token Index: 679

Text #6

Max Range: 0.5245. Min Range: -0.5245

Max Act: 0.4523. Min Act: -0.0000

Data Index: 563738 (C4 (Web Text))

Max Activating Token Index: 968

Text #7

Max Range: 0.5245. Min Range: -0.5245

Max Act: 0.4327. Min Act: -0.0000

Data Index: 958357 (C4 (Web Text))

Max Activating Token Index: 349

Text #8

Max Range: 0.5245. Min Range: -0.5245

Max Act: 0.4180. Min Act: -0.0000

Data Index: 121630 (C4 (Web Text))

Max Activating Token Index: 433

Text #9

Max Range: 0.5245. Min Range: -0.5245

Max Act: 0.4383. Min Act: -0.0001

Data Index: 1285845 (C4 (Web Text))

Max Activating Token Index: 596

Text #10

Max Range: 0.5245. Min Range: -0.5245

Max Act: 0.4216. Min Act: -0.0001

Data Index: 185402 (C4 (Web Text))

Max Activating Token Index: 375

Text #11

Max Range: 0.5245. Min Range: -0.5245

Max Act: 0.4485. Min Act: -0.0000

Data Index: 280809 (C4 (Web Text))

Max Activating Token Index: 968

Text #12

Max Range: 0.5245. Min Range: -0.5245

Max Act: 0.4651. Min Act: -0.0001

Data Index: 371711 (C4 (Web Text))

Max Activating Token Index: 1004

Text #13

Max Range: 0.5245. Min Range: -0.5245

Max Act: 0.4157. Min Act: -0.0000

Data Index: 585205 (C4 (Web Text))

Max Activating Token Index: 994

Text #14

Max Range: 0.5245. Min Range: -0.5245

Max Act: 0.4402. Min Act: -0.0001

Data Index: 515868 (C4 (Web Text))

Max Activating Token Index: 591

Text #15

Max Range: 0.5245. Min Range: -0.5245

Max Act: 0.4252. Min Act: -0.0001

Data Index: 771520 (C4 (Web Text))

Max Activating Token Index: 1013

Text #16

Max Range: 0.5245. Min Range: -0.5245

Max Act: 0.4145. Min Act: -0.0001

Data Index: 669362 (C4 (Web Text))

Max Activating Token Index: 535

Text #17

Max Range: 0.5245. Min Range: -0.5245

Max Act: 0.4135. Min Act: -0.0001

Data Index: 380086 (C4 (Web Text))

Max Activating Token Index: 847

Text #18

Max Range: 0.5245. Min Range: -0.5245

Max Act: 0.4031. Min Act: -0.0000

Data Index: 558949 (C4 (Web Text))

Max Activating Token Index: 280

Text #19

Max Range: 0.5245. Min Range: -0.5245

Max Act: 0.3806. Min Act: -0.0000

Data Index: 1076007 (C4 (Web Text))

Max Activating Token Index: 236