Model: SoLU Model: 2 Layers, 2048 Neurons per Layer

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

Neuron 501 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-2l')

Text #0

Max Range: 0.0523. Min Range: -0.0523

Max Act: 0.0523. Min Act: -0.0003

Data Index: 357662 (C4 (Web Text))

Max Activating Token Index: 135

Text #1

Max Range: 0.0523. Min Range: -0.0523

Max Act: 0.0410. Min Act: -0.0003

Data Index: 827239 (C4 (Web Text))

Max Activating Token Index: 137

Text #2

Max Range: 0.0523. Min Range: -0.0523

Max Act: 0.0410. Min Act: -0.0003

Data Index: 919390 (C4 (Web Text))

Max Activating Token Index: 539

Text #3

Max Range: 0.0523. Min Range: -0.0523

Max Act: 0.0406. Min Act: -0.0003

Data Index: 606743 (C4 (Web Text))

Max Activating Token Index: 53

Text #4

Max Range: 0.0523. Min Range: -0.0523

Max Act: 0.0380. Min Act: -0.0004

Data Index: 125030 (C4 (Web Text))

Max Activating Token Index: 423

Text #5

Max Range: 0.0523. Min Range: -0.0523

Max Act: 0.0360. Min Act: -0.0003

Data Index: 722276 (C4 (Web Text))

Max Activating Token Index: 274

Text #6

Max Range: 0.0523. Min Range: -0.0523

Max Act: 0.0394. Min Act: -0.0003

Data Index: 772129 (C4 (Web Text))

Max Activating Token Index: 270

Text #7

Max Range: 0.0523. Min Range: -0.0523

Max Act: 0.0400. Min Act: -0.0003

Data Index: 1132520 (C4 (Web Text))

Max Activating Token Index: 519

Text #8

Max Range: 0.0523. Min Range: -0.0523

Max Act: 0.0372. Min Act: -0.0003

Data Index: 233219 (C4 (Web Text))

Max Activating Token Index: 300

Text #9

Max Range: 0.0523. Min Range: -0.0523

Max Act: 0.0390. Min Act: -0.0003

Data Index: 791166 (C4 (Web Text))

Max Activating Token Index: 210

Text #10

Max Range: 0.0523. Min Range: -0.0523

Max Act: 0.0387. Min Act: -0.0003

Data Index: 774247 (C4 (Web Text))

Max Activating Token Index: 293

Text #11

Max Range: 0.0523. Min Range: -0.0523

Max Act: 0.0370. Min Act: -0.0004

Data Index: 1193141 (C4 (Web Text))

Max Activating Token Index: 78

Text #12

Max Range: 0.0523. Min Range: -0.0523

Max Act: 0.0359. Min Act: -0.0003

Data Index: 1346797 (C4 (Web Text))

Max Activating Token Index: 647

Text #13

Max Range: 0.0523. Min Range: -0.0523

Max Act: 0.0356. Min Act: -0.0003

Data Index: 758331 (C4 (Web Text))

Max Activating Token Index: 1008

Text #14

Max Range: 0.0523. Min Range: -0.0523

Max Act: 0.0378. Min Act: -0.0003

Data Index: 1215509 (C4 (Web Text))

Max Activating Token Index: 497

Text #15

Max Range: 0.0523. Min Range: -0.0523

Max Act: 0.0356. Min Act: -0.0003

Data Index: 1325231 (C4 (Web Text))

Max Activating Token Index: 228

Text #16

Max Range: 0.0523. Min Range: -0.0523

Max Act: 0.0327. Min Act: -0.0004

Data Index: 291692 (C4 (Web Text))

Max Activating Token Index: 845

Text #17

Max Range: 0.0523. Min Range: -0.0523

Max Act: 0.0365. Min Act: -0.0003

Data Index: 1081453 (C4 (Web Text))

Max Activating Token Index: 23

Text #18

Max Range: 0.0523. Min Range: -0.0523

Max Act: 0.0353. Min Act: -0.0003

Data Index: 427394 (C4 (Web Text))

Max Activating Token Index: 984

Text #19

Max Range: 0.0523. Min Range: -0.0523

Max Act: 0.0327. Min Act: -0.0004

Data Index: 761944 (C4 (Web Text))

Max Activating Token Index: 677