Model: SoLU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 797 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')

Text #0

Max Range: 0.0229. Min Range: -0.0229

Max Act: 0.0229. Min Act: -0.0006

Data Index: 442734 (C4 (Web Text))

Max Activating Token Index: 19

Text #1

Max Range: 0.0229. Min Range: -0.0229

Max Act: 0.0197. Min Act: -0.0006

Data Index: 728686 (C4 (Web Text))

Max Activating Token Index: 279

Text #2

Max Range: 0.0229. Min Range: -0.0229

Max Act: 0.0205. Min Act: -0.0006

Data Index: 388447 (C4 (Web Text))

Max Activating Token Index: 608

Text #3

Max Range: 0.0229. Min Range: -0.0229

Max Act: 0.0191. Min Act: -0.0006

Data Index: 407823 (C4 (Web Text))

Max Activating Token Index: 949

Text #4

Max Range: 0.0229. Min Range: -0.0229

Max Act: 0.0203. Min Act: -0.0006

Data Index: 640543 (C4 (Web Text))

Max Activating Token Index: 117

Text #5

Max Range: 0.0229. Min Range: -0.0229

Max Act: 0.0192. Min Act: -0.0006

Data Index: 1579908 (Python Code)

Max Activating Token Index: 373

Text #6

Max Range: 0.0229. Min Range: -0.0229

Max Act: 0.0197. Min Act: -0.0006

Data Index: 1622492 (Python Code)

Max Activating Token Index: 438

Text #7

Max Range: 0.0229. Min Range: -0.0229

Max Act: 0.0201. Min Act: -0.0005

Data Index: 1114255 (C4 (Web Text))

Max Activating Token Index: 927

Text #8

Max Range: 0.0229. Min Range: -0.0229

Max Act: 0.0189. Min Act: -0.0005

Data Index: 154420 (C4 (Web Text))

Max Activating Token Index: 726

Text #9

Max Range: 0.0229. Min Range: -0.0229

Max Act: 0.0182. Min Act: -0.0006

Data Index: 918422 (C4 (Web Text))

Max Activating Token Index: 633

Text #10

Max Range: 0.0229. Min Range: -0.0229

Max Act: 0.0190. Min Act: -0.0006

Data Index: 133787 (C4 (Web Text))

Max Activating Token Index: 20

Text #11

Max Range: 0.0229. Min Range: -0.0229

Max Act: 0.0185. Min Act: -0.0006

Data Index: 495832 (C4 (Web Text))

Max Activating Token Index: 473

Text #12

Max Range: 0.0229. Min Range: -0.0229

Max Act: 0.0185. Min Act: -0.0006

Data Index: 984601 (C4 (Web Text))

Max Activating Token Index: 867

Text #13

Max Range: 0.0229. Min Range: -0.0229

Max Act: 0.0188. Min Act: -0.0006

Data Index: 103513 (C4 (Web Text))

Max Activating Token Index: 458

Text #14

Max Range: 0.0229. Min Range: -0.0229

Max Act: 0.0187. Min Act: -0.0006

Data Index: 1090974 (C4 (Web Text))

Max Activating Token Index: 649

Text #15

Max Range: 0.0229. Min Range: -0.0229

Max Act: 0.0183. Min Act: -0.0006

Data Index: 1406279 (Python Code)

Max Activating Token Index: 735

Text #16

Max Range: 0.0229. Min Range: -0.0229

Max Act: 0.0188. Min Act: -0.0006

Data Index: 1277464 (C4 (Web Text))

Max Activating Token Index: 280

Text #17

Max Range: 0.0229. Min Range: -0.0229

Max Act: 0.0183. Min Act: -0.0006

Data Index: 546560 (C4 (Web Text))

Max Activating Token Index: 23

Text #18

Max Range: 0.0229. Min Range: -0.0229

Max Act: 0.0191. Min Act: -0.0006

Data Index: 1426676 (Python Code)

Max Activating Token Index: 893

Text #19

Max Range: 0.0229. Min Range: -0.0229

Max Act: 0.0185. Min Act: -0.0006

Data Index: 619252 (C4 (Web Text))

Max Activating Token Index: 792