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

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

Neuron 5089 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7664. Min Range: -0.7664

Max Act: 0.7664. Min Act: -0.0000

Data Index: 556197 (C4 (Web Text))

Max Activating Token Index: 779

Text #1

Max Range: 0.7664. Min Range: -0.7664

Max Act: 0.7173. Min Act: -0.0000

Data Index: 218260 (C4 (Web Text))

Max Activating Token Index: 989

Text #2

Max Range: 0.7664. Min Range: -0.7664

Max Act: 0.7305. Min Act: -0.0000

Data Index: 603629 (C4 (Web Text))

Max Activating Token Index: 396

Text #3

Max Range: 0.7664. Min Range: -0.7664

Max Act: 0.7085. Min Act: -0.0000

Data Index: 731126 (C4 (Web Text))

Max Activating Token Index: 171

Text #4

Max Range: 0.7664. Min Range: -0.7664

Max Act: 0.6970. Min Act: -0.0000

Data Index: 151994 (C4 (Web Text))

Max Activating Token Index: 239

Text #5

Max Range: 0.7664. Min Range: -0.7664

Max Act: 0.7502. Min Act: -0.0000

Data Index: 480416 (C4 (Web Text))

Max Activating Token Index: 422

Text #6

Max Range: 0.7664. Min Range: -0.7664

Max Act: 0.7103. Min Act: -0.0000

Data Index: 406064 (C4 (Web Text))

Max Activating Token Index: 135

Text #7

Max Range: 0.7664. Min Range: -0.7664

Max Act: 0.7052. Min Act: -0.0000

Data Index: 654421 (C4 (Web Text))

Max Activating Token Index: 235

Text #8

Max Range: 0.7664. Min Range: -0.7664

Max Act: 0.7210. Min Act: -0.0000

Data Index: 724969 (C4 (Web Text))

Max Activating Token Index: 309

Text #9

Max Range: 0.7664. Min Range: -0.7664

Max Act: 0.6947. Min Act: -0.0000

Data Index: 708824 (C4 (Web Text))

Max Activating Token Index: 381

Text #10

Max Range: 0.7664. Min Range: -0.7664

Max Act: 0.6512. Min Act: -0.0000

Data Index: 733439 (C4 (Web Text))

Max Activating Token Index: 802

Text #11

Max Range: 0.7664. Min Range: -0.7664

Max Act: 0.6672. Min Act: -0.0000

Data Index: 424230 (C4 (Web Text))

Max Activating Token Index: 176

Text #12

Max Range: 0.7664. Min Range: -0.7664

Max Act: 0.6621. Min Act: -0.0000

Data Index: 1242013 (C4 (Web Text))

Max Activating Token Index: 417

Text #13

Max Range: 0.7664. Min Range: -0.7664

Max Act: 0.6591. Min Act: -0.0000

Data Index: 584526 (C4 (Web Text))

Max Activating Token Index: 151

Text #14

Max Range: 0.7664. Min Range: -0.7664

Max Act: 0.6320. Min Act: -0.0000

Data Index: 121927 (C4 (Web Text))

Max Activating Token Index: 242

Text #15

Max Range: 0.7664. Min Range: -0.7664

Max Act: 0.6648. Min Act: -0.0000

Data Index: 499097 (C4 (Web Text))

Max Activating Token Index: 244

Text #16

Max Range: 0.7664. Min Range: -0.7664

Max Act: 0.6598. Min Act: -0.0000

Data Index: 420683 (C4 (Web Text))

Max Activating Token Index: 231

Text #17

Max Range: 0.7664. Min Range: -0.7664

Max Act: 0.6576. Min Act: -0.0000

Data Index: 71391 (C4 (Web Text))

Max Activating Token Index: 506

Text #18

Max Range: 0.7664. Min Range: -0.7664

Max Act: 0.6139. Min Act: -0.0000

Data Index: 445339 (C4 (Web Text))

Max Activating Token Index: 475

Text #19

Max Range: 0.7664. Min Range: -0.7664

Max Act: 0.6176. Min Act: -0.0000

Data Index: 714778 (C4 (Web Text))

Max Activating Token Index: 295