Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 1679 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.6745. Min Range: -0.6745

Max Act: 0.6363. Min Act: -0.0001

Data Index: 726019 (C4 (Web Text))

Max Activating Token Index: 178

Text #1

Max Range: 0.6745. Min Range: -0.6745

Max Act: 0.6358. Min Act: -0.0001

Data Index: 1332753 (C4 (Web Text))

Max Activating Token Index: 203

Text #2

Max Range: 0.6745. Min Range: -0.6745

Max Act: 0.6431. Min Act: -0.0001

Data Index: 525391 (C4 (Web Text))

Max Activating Token Index: 234

Text #3

Max Range: 0.6745. Min Range: -0.6745

Max Act: 0.6369. Min Act: -0.0001

Data Index: 4629 (C4 (Web Text))

Max Activating Token Index: 332

Text #4

Max Range: 0.6745. Min Range: -0.6745

Max Act: 0.6745. Min Act: -0.0001

Data Index: 911332 (C4 (Web Text))

Max Activating Token Index: 807

Text #5

Max Range: 0.6745. Min Range: -0.6745

Max Act: 0.6406. Min Act: -0.0001

Data Index: 640244 (C4 (Web Text))

Max Activating Token Index: 806

Text #6

Max Range: 0.6745. Min Range: -0.6745

Max Act: 0.6089. Min Act: -0.0001

Data Index: 941546 (C4 (Web Text))

Max Activating Token Index: 891

Text #7

Max Range: 0.6745. Min Range: -0.6745

Max Act: 0.6427. Min Act: -0.0001

Data Index: 822806 (C4 (Web Text))

Max Activating Token Index: 184

Text #8

Max Range: 0.6745. Min Range: -0.6745

Max Act: 0.5474. Min Act: -0.0001

Data Index: 918186 (C4 (Web Text))

Max Activating Token Index: 619

Text #9

Max Range: 0.6745. Min Range: -0.6745

Max Act: 0.5779. Min Act: -0.0001

Data Index: 1133151 (C4 (Web Text))

Max Activating Token Index: 132

Text #10

Max Range: 0.6745. Min Range: -0.6745

Max Act: 0.5192. Min Act: -0.0001

Data Index: 712184 (C4 (Web Text))

Max Activating Token Index: 670

Text #11

Max Range: 0.6745. Min Range: -0.6745

Max Act: 0.5713. Min Act: -0.0001

Data Index: 1227064 (C4 (Web Text))

Max Activating Token Index: 364

Text #12

Max Range: 0.6745. Min Range: -0.6745

Max Act: 0.6323. Min Act: -0.0001

Data Index: 496895 (C4 (Web Text))

Max Activating Token Index: 668

Text #13

Max Range: 0.6745. Min Range: -0.6745

Max Act: 0.6502. Min Act: -0.0001

Data Index: 115768 (C4 (Web Text))

Max Activating Token Index: 813

Text #14

Max Range: 0.6745. Min Range: -0.6745

Max Act: 0.5508. Min Act: -0.0001

Data Index: 439651 (C4 (Web Text))

Max Activating Token Index: 857

Text #15

Max Range: 0.6745. Min Range: -0.6745

Max Act: 0.4725. Min Act: -0.0001

Data Index: 651904 (C4 (Web Text))

Max Activating Token Index: 584

Text #16

Max Range: 0.6745. Min Range: -0.6745

Max Act: 0.6274. Min Act: -0.0001

Data Index: 1152387 (C4 (Web Text))

Max Activating Token Index: 724

Text #17

Max Range: 0.6745. Min Range: -0.6745

Max Act: 0.6532. Min Act: -0.0001

Data Index: 1168153 (C4 (Web Text))

Max Activating Token Index: 766

Text #18

Max Range: 0.6745. Min Range: -0.6745

Max Act: 0.5048. Min Act: -0.0001

Data Index: 513365 (C4 (Web Text))

Max Activating Token Index: 668

Text #19

Max Range: 0.6745. Min Range: -0.6745

Max Act: 0.6323. Min Act: -0.0001

Data Index: 749156 (C4 (Web Text))

Max Activating Token Index: 824