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

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

Neuron 918 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: 2.5247. Min Range: -2.5247

Max Act: 2.5247. Min Act: -0.0000

Data Index: 408191 (C4 (Web Text))

Max Activating Token Index: 85

Text #1

Max Range: 2.5247. Min Range: -2.5247

Max Act: 1.9054. Min Act: -0.0000

Data Index: 346536 (C4 (Web Text))

Max Activating Token Index: 699

Text #2

Max Range: 2.5247. Min Range: -2.5247

Max Act: 1.8496. Min Act: -0.0000

Data Index: 339677 (C4 (Web Text))

Max Activating Token Index: 264

Text #3

Max Range: 2.5247. Min Range: -2.5247

Max Act: 1.8402. Min Act: -0.0000

Data Index: 1274346 (C4 (Web Text))

Max Activating Token Index: 816

Text #4

Max Range: 2.5247. Min Range: -2.5247

Max Act: 1.8513. Min Act: -0.0000

Data Index: 246633 (C4 (Web Text))

Max Activating Token Index: 41

Text #5

Max Range: 2.5247. Min Range: -2.5247

Max Act: 1.5973. Min Act: -0.0000

Data Index: 353203 (C4 (Web Text))

Max Activating Token Index: 253

Text #6

Max Range: 2.5247. Min Range: -2.5247

Max Act: 1.8613. Min Act: -0.0000

Data Index: 490934 (C4 (Web Text))

Max Activating Token Index: 398

Text #7

Max Range: 2.5247. Min Range: -2.5247

Max Act: 1.6452. Min Act: -0.0000

Data Index: 1231027 (C4 (Web Text))

Max Activating Token Index: 969

Text #8

Max Range: 2.5247. Min Range: -2.5247

Max Act: 1.8317. Min Act: -0.0000

Data Index: 1546476 (Python Code)

Max Activating Token Index: 127

Text #9

Max Range: 2.5247. Min Range: -2.5247

Max Act: 1.5993. Min Act: -0.0000

Data Index: 117156 (C4 (Web Text))

Max Activating Token Index: 651

Text #10

Max Range: 2.5247. Min Range: -2.5247

Max Act: 1.5768. Min Act: -0.0000

Data Index: 217105 (C4 (Web Text))

Max Activating Token Index: 880

Text #11

Max Range: 2.5247. Min Range: -2.5247

Max Act: 1.6367. Min Act: -0.0000

Data Index: 465197 (C4 (Web Text))

Max Activating Token Index: 391

Text #12

Max Range: 2.5247. Min Range: -2.5247

Max Act: 1.5220. Min Act: -0.0000

Data Index: 68367 (C4 (Web Text))

Max Activating Token Index: 827

Text #13

Max Range: 2.5247. Min Range: -2.5247

Max Act: 1.5138. Min Act: -0.0000

Data Index: 452009 (C4 (Web Text))

Max Activating Token Index: 720

Text #14

Max Range: 2.5247. Min Range: -2.5247

Max Act: 1.5926. Min Act: -0.0000

Data Index: 106584 (C4 (Web Text))

Max Activating Token Index: 469

Text #15

Max Range: 2.5247. Min Range: -2.5247

Max Act: 1.5155. Min Act: -0.0000

Data Index: 183989 (C4 (Web Text))

Max Activating Token Index: 834

Text #16

Max Range: 2.5247. Min Range: -2.5247

Max Act: 1.4975. Min Act: -0.0000

Data Index: 1165761 (C4 (Web Text))

Max Activating Token Index: 230

Text #17

Max Range: 2.5247. Min Range: -2.5247

Max Act: 1.5764. Min Act: -0.0000

Data Index: 612032 (C4 (Web Text))

Max Activating Token Index: 728

Text #18

Max Range: 2.5247. Min Range: -2.5247

Max Act: 1.4920. Min Act: -0.0000

Data Index: 453146 (C4 (Web Text))

Max Activating Token Index: 707

Text #19

Max Range: 2.5247. Min Range: -2.5247

Max Act: 1.5549. Min Act: -0.0000

Data Index: 772609 (C4 (Web Text))

Max Activating Token Index: 625