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

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

Neuron 2186 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.7239. Min Range: -1.7239

Max Act: 1.7239. Min Act: -0.0000

Data Index: 14266 (C4 (Web Text))

Max Activating Token Index: 464

Text #1

Max Range: 1.7239. Min Range: -1.7239

Max Act: 1.4545. Min Act: -0.0000

Data Index: 953294 (C4 (Web Text))

Max Activating Token Index: 527

Text #2

Max Range: 1.7239. Min Range: -1.7239

Max Act: 1.3967. Min Act: -0.0000

Data Index: 590791 (C4 (Web Text))

Max Activating Token Index: 359

Text #3

Max Range: 1.7239. Min Range: -1.7239

Max Act: 1.3845. Min Act: -0.0000

Data Index: 1256933 (C4 (Web Text))

Max Activating Token Index: 519

Text #4

Max Range: 1.7239. Min Range: -1.7239

Max Act: 1.2727. Min Act: -0.0000

Data Index: 67838 (C4 (Web Text))

Max Activating Token Index: 381

Text #5

Max Range: 1.7239. Min Range: -1.7239

Max Act: 1.2143. Min Act: -0.0000

Data Index: 47693 (C4 (Web Text))

Max Activating Token Index: 434

Text #6

Max Range: 1.7239. Min Range: -1.7239

Max Act: 1.1581. Min Act: -0.0000

Data Index: 750615 (C4 (Web Text))

Max Activating Token Index: 944

Text #7

Max Range: 1.7239. Min Range: -1.7239

Max Act: 1.3809. Min Act: -0.0000

Data Index: 421850 (C4 (Web Text))

Max Activating Token Index: 1019

Text #8

Max Range: 1.7239. Min Range: -1.7239

Max Act: 1.1476. Min Act: -0.0000

Data Index: 567322 (C4 (Web Text))

Max Activating Token Index: 526

Text #9

Max Range: 1.7239. Min Range: -1.7239

Max Act: 1.1567. Min Act: -0.0000

Data Index: 188634 (C4 (Web Text))

Max Activating Token Index: 834

Text #10

Max Range: 1.7239. Min Range: -1.7239

Max Act: 1.1864. Min Act: -0.0000

Data Index: 501722 (C4 (Web Text))

Max Activating Token Index: 394

Text #11

Max Range: 1.7239. Min Range: -1.7239

Max Act: 1.0756. Min Act: -0.0000

Data Index: 278080 (C4 (Web Text))

Max Activating Token Index: 768

Text #12

Max Range: 1.7239. Min Range: -1.7239

Max Act: 1.0174. Min Act: -0.0000

Data Index: 27859 (C4 (Web Text))

Max Activating Token Index: 152

Text #13

Max Range: 1.7239. Min Range: -1.7239

Max Act: 1.1128. Min Act: -0.0000

Data Index: 1072529 (C4 (Web Text))

Max Activating Token Index: 225

Text #14

Max Range: 1.7239. Min Range: -1.7239

Max Act: 1.0397. Min Act: -0.0000

Data Index: 1456125 (Python Code)

Max Activating Token Index: 169

Text #15

Max Range: 1.7239. Min Range: -1.7239

Max Act: 0.9851. Min Act: -0.0000

Data Index: 957187 (C4 (Web Text))

Max Activating Token Index: 645

Text #16

Max Range: 1.7239. Min Range: -1.7239

Max Act: 1.0798. Min Act: -0.0000

Data Index: 814974 (C4 (Web Text))

Max Activating Token Index: 65

Text #17

Max Range: 1.7239. Min Range: -1.7239

Max Act: 1.0381. Min Act: -0.0000

Data Index: 847166 (C4 (Web Text))

Max Activating Token Index: 699

Text #18

Max Range: 1.7239. Min Range: -1.7239

Max Act: 1.0419. Min Act: -0.0000

Data Index: 606368 (C4 (Web Text))

Max Activating Token Index: 404

Text #19

Max Range: 1.7239. Min Range: -1.7239

Max Act: 1.0215. Min Act: -0.0000

Data Index: 1140128 (C4 (Web Text))

Max Activating Token Index: 721