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

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

Neuron 643 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7991. Min Range: -0.7991

Max Act: 0.6647. Min Act: -0.0000

Data Index: 144152 (C4 (Web Text))

Max Activating Token Index: 813

Text #1

Max Range: 0.7991. Min Range: -0.7991

Max Act: 0.7923. Min Act: -0.0000

Data Index: 116408 (C4 (Web Text))

Max Activating Token Index: 228

Text #2

Max Range: 0.7991. Min Range: -0.7991

Max Act: 0.7368. Min Act: -0.0000

Data Index: 647602 (C4 (Web Text))

Max Activating Token Index: 267

Text #3

Max Range: 0.7991. Min Range: -0.7991

Max Act: 0.7132. Min Act: -0.0000

Data Index: 149132 (C4 (Web Text))

Max Activating Token Index: 199

Text #4

Max Range: 0.7991. Min Range: -0.7991

Max Act: 0.7242. Min Act: -0.0000

Data Index: 433418 (C4 (Web Text))

Max Activating Token Index: 191

Text #5

Max Range: 0.7991. Min Range: -0.7991

Max Act: 0.7991. Min Act: -0.0000

Data Index: 618386 (C4 (Web Text))

Max Activating Token Index: 248

Text #6

Max Range: 0.7991. Min Range: -0.7991

Max Act: 0.6668. Min Act: -0.0000

Data Index: 750504 (C4 (Web Text))

Max Activating Token Index: 415

Text #7

Max Range: 0.7991. Min Range: -0.7991

Max Act: 0.6040. Min Act: -0.0000

Data Index: 203552 (C4 (Web Text))

Max Activating Token Index: 300

Text #8

Max Range: 0.7991. Min Range: -0.7991

Max Act: 0.6498. Min Act: -0.0000

Data Index: 702019 (C4 (Web Text))

Max Activating Token Index: 630

Text #9

Max Range: 0.7991. Min Range: -0.7991

Max Act: 0.6290. Min Act: -0.0000

Data Index: 1296588 (C4 (Web Text))

Max Activating Token Index: 338

Text #10

Max Range: 0.7991. Min Range: -0.7991

Max Act: 0.6306. Min Act: -0.0000

Data Index: 184941 (C4 (Web Text))

Max Activating Token Index: 391

Text #11

Max Range: 0.7991. Min Range: -0.7991

Max Act: 0.6154. Min Act: -0.0000

Data Index: 423675 (C4 (Web Text))

Max Activating Token Index: 963

Text #12

Max Range: 0.7991. Min Range: -0.7991

Max Act: 0.6858. Min Act: -0.0000

Data Index: 1026635 (C4 (Web Text))

Max Activating Token Index: 272

Text #13

Max Range: 0.7991. Min Range: -0.7991

Max Act: 0.6460. Min Act: -0.0000

Data Index: 789701 (C4 (Web Text))

Max Activating Token Index: 76

Text #14

Max Range: 0.7991. Min Range: -0.7991

Max Act: 0.6195. Min Act: -0.0000

Data Index: 919677 (C4 (Web Text))

Max Activating Token Index: 488

Text #15

Max Range: 0.7991. Min Range: -0.7991

Max Act: 0.6264. Min Act: -0.0000

Data Index: 194149 (C4 (Web Text))

Max Activating Token Index: 79

Text #16

Max Range: 0.7991. Min Range: -0.7991

Max Act: 0.5251. Min Act: -0.0000

Data Index: 1275576 (C4 (Web Text))

Max Activating Token Index: 508

Text #17

Max Range: 0.7991. Min Range: -0.7991

Max Act: 0.6559. Min Act: -0.0000

Data Index: 1244264 (C4 (Web Text))

Max Activating Token Index: 536

Text #18

Max Range: 0.7991. Min Range: -0.7991

Max Act: 0.5407. Min Act: -0.0000

Data Index: 1125573 (C4 (Web Text))

Max Activating Token Index: 202

Text #19

Max Range: 0.7991. Min Range: -0.7991

Max Act: 0.5819. Min Act: -0.0000

Data Index: 152121 (C4 (Web Text))

Max Activating Token Index: 589