Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 6017 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 10.5438. Min Range: -10.5438

Max Act: 10.5438. Min Act: -0.0002

Data Index: 661107 (C4 (Web Text))

Max Activating Token Index: 112

Text #1

Max Range: 10.5438. Min Range: -10.5438

Max Act: 10.5247. Min Act: -0.0002

Data Index: 663627 (C4 (Web Text))

Max Activating Token Index: 226

Text #2

Max Range: 10.5438. Min Range: -10.5438

Max Act: 10.4839. Min Act: -0.0002

Data Index: 1070025 (C4 (Web Text))

Max Activating Token Index: 417

Text #3

Max Range: 10.5438. Min Range: -10.5438

Max Act: 10.3854. Min Act: -0.0002

Data Index: 6870 (C4 (Web Text))

Max Activating Token Index: 305

Text #4

Max Range: 10.5438. Min Range: -10.5438

Max Act: 10.5386. Min Act: -0.0002

Data Index: 948882 (C4 (Web Text))

Max Activating Token Index: 488

Text #5

Max Range: 10.5438. Min Range: -10.5438

Max Act: 10.4396. Min Act: -0.0002

Data Index: 1276187 (C4 (Web Text))

Max Activating Token Index: 841

Text #6

Max Range: 10.5438. Min Range: -10.5438

Max Act: 10.4008. Min Act: -0.0002

Data Index: 975353 (C4 (Web Text))

Max Activating Token Index: 814

Text #7

Max Range: 10.5438. Min Range: -10.5438

Max Act: 10.5003. Min Act: -0.0002

Data Index: 1264550 (C4 (Web Text))

Max Activating Token Index: 191

Text #8

Max Range: 10.5438. Min Range: -10.5438

Max Act: 10.3614. Min Act: -0.0002

Data Index: 663581 (C4 (Web Text))

Max Activating Token Index: 346

Text #9

Max Range: 10.5438. Min Range: -10.5438

Max Act: 10.2573. Min Act: -0.0002

Data Index: 903099 (C4 (Web Text))

Max Activating Token Index: 674

Text #10

Max Range: 10.5438. Min Range: -10.5438

Max Act: 10.2041. Min Act: -0.0002

Data Index: 369413 (C4 (Web Text))

Max Activating Token Index: 535

Text #11

Max Range: 10.5438. Min Range: -10.5438

Max Act: 10.2904. Min Act: -0.0002

Data Index: 1090907 (C4 (Web Text))

Max Activating Token Index: 445

Text #12

Max Range: 10.5438. Min Range: -10.5438

Max Act: 10.1846. Min Act: -0.0002

Data Index: 313683 (C4 (Web Text))

Max Activating Token Index: 193

Text #13

Max Range: 10.5438. Min Range: -10.5438

Max Act: 10.2783. Min Act: -0.0002

Data Index: 1334740 (C4 (Web Text))

Max Activating Token Index: 699

Text #14

Max Range: 10.5438. Min Range: -10.5438

Max Act: 10.2712. Min Act: -0.0002

Data Index: 7603 (C4 (Web Text))

Max Activating Token Index: 918

Text #15

Max Range: 10.5438. Min Range: -10.5438

Max Act: 10.1558. Min Act: -0.0002

Data Index: 830169 (C4 (Web Text))

Max Activating Token Index: 412

Text #16

Max Range: 10.5438. Min Range: -10.5438

Max Act: 10.2469. Min Act: -0.0002

Data Index: 559778 (C4 (Web Text))

Max Activating Token Index: 684

Text #17

Max Range: 10.5438. Min Range: -10.5438

Max Act: 10.1486. Min Act: -0.0002

Data Index: 1103988 (C4 (Web Text))

Max Activating Token Index: 337

Text #18

Max Range: 10.5438. Min Range: -10.5438

Max Act: 10.2407. Min Act: -0.0002

Data Index: 807172 (C4 (Web Text))

Max Activating Token Index: 215

Text #19

Max Range: 10.5438. Min Range: -10.5438

Max Act: 10.3340. Min Act: -0.0002

Data Index: 304891 (C4 (Web Text))

Max Activating Token Index: 763