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

Dataset: The Pile

Neuron 1336 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 10.0295. Min Range: -10.0295

Max Act: 10.0295. Min Act: -0.0000

Data Index: 255141 (The Pile)

Max Activating Token Index: 180

Text #1

Max Range: 10.0295. Min Range: -10.0295

Max Act: 9.9403. Min Act: -0.0000

Data Index: 739965 (The Pile)

Max Activating Token Index: 324

Text #2

Max Range: 10.0295. Min Range: -10.0295

Max Act: 9.8708. Min Act: -0.0000

Data Index: 1917021 (The Pile)

Max Activating Token Index: 86

Text #3

Max Range: 10.0295. Min Range: -10.0295

Max Act: 9.7113. Min Act: -0.0000

Data Index: 1787708 (The Pile)

Max Activating Token Index: 140

Text #4

Max Range: 10.0295. Min Range: -10.0295

Max Act: 9.4128. Min Act: -0.0000

Data Index: 512813 (The Pile)

Max Activating Token Index: 286

Text #5

Max Range: 10.0295. Min Range: -10.0295

Max Act: 9.6213. Min Act: -0.0000

Data Index: 416330 (The Pile)

Max Activating Token Index: 136

Text #6

Max Range: 10.0295. Min Range: -10.0295

Max Act: 9.5134. Min Act: -0.0000

Data Index: 738305 (The Pile)

Max Activating Token Index: 226

Text #7

Max Range: 10.0295. Min Range: -10.0295

Max Act: 9.8637. Min Act: -0.0000

Data Index: 127600 (The Pile)

Max Activating Token Index: 323

Text #8

Max Range: 10.0295. Min Range: -10.0295

Max Act: 9.6168. Min Act: -0.0000

Data Index: 937830 (The Pile)

Max Activating Token Index: 210

Text #9

Max Range: 10.0295. Min Range: -10.0295

Max Act: 9.5304. Min Act: -0.0000

Data Index: 210438 (The Pile)

Max Activating Token Index: 333

Text #10

Max Range: 10.0295. Min Range: -10.0295

Max Act: 9.3102. Min Act: -0.0000

Data Index: 980069 (The Pile)

Max Activating Token Index: 513

Text #11

Max Range: 10.0295. Min Range: -10.0295

Max Act: 9.4153. Min Act: -0.0000

Data Index: 1335926 (The Pile)

Max Activating Token Index: 825

Text #12

Max Range: 10.0295. Min Range: -10.0295

Max Act: 9.6452. Min Act: -0.0000

Data Index: 1502727 (The Pile)

Max Activating Token Index: 233

Text #13

Max Range: 10.0295. Min Range: -10.0295

Max Act: 9.2778. Min Act: -0.0000

Data Index: 76805 (The Pile)

Max Activating Token Index: 491

Text #14

Max Range: 10.0295. Min Range: -10.0295

Max Act: 9.0844. Min Act: -0.0000

Data Index: 20095 (The Pile)

Max Activating Token Index: 381

Text #15

Max Range: 10.0295. Min Range: -10.0295

Max Act: 9.2993. Min Act: -0.0000

Data Index: 422743 (The Pile)

Max Activating Token Index: 118

Text #16

Max Range: 10.0295. Min Range: -10.0295

Max Act: 9.3437. Min Act: -0.0000

Data Index: 437301 (The Pile)

Max Activating Token Index: 699

Text #17

Max Range: 10.0295. Min Range: -10.0295

Max Act: 8.7672. Min Act: -0.0000

Data Index: 821733 (The Pile)

Max Activating Token Index: 567

Text #18

Max Range: 10.0295. Min Range: -10.0295

Max Act: 8.7576. Min Act: -0.0000

Data Index: 1875291 (The Pile)

Max Activating Token Index: 612

Text #19

Max Range: 10.0295. Min Range: -10.0295

Max Act: 8.9293. Min Act: -0.0000

Data Index: 741559 (The Pile)

Max Activating Token Index: 320