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

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

Neuron 879 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: 1.5242. Min Range: -1.5242

Max Act: 1.4925. Min Act: -0.0000

Data Index: 662590 (C4 (Web Text))

Max Activating Token Index: 601

Text #1

Max Range: 1.5242. Min Range: -1.5242

Max Act: 1.5242. Min Act: -0.0000

Data Index: 1353415 (C4 (Web Text))

Max Activating Token Index: 68

Text #2

Max Range: 1.5242. Min Range: -1.5242

Max Act: 1.3642. Min Act: -0.0000

Data Index: 236949 (C4 (Web Text))

Max Activating Token Index: 885

Text #3

Max Range: 1.5242. Min Range: -1.5242

Max Act: 1.3271. Min Act: -0.0000

Data Index: 69726 (C4 (Web Text))

Max Activating Token Index: 857

Text #4

Max Range: 1.5242. Min Range: -1.5242

Max Act: 1.3111. Min Act: -0.0000

Data Index: 539607 (C4 (Web Text))

Max Activating Token Index: 79

Text #5

Max Range: 1.5242. Min Range: -1.5242

Max Act: 1.2345. Min Act: -0.0000

Data Index: 366072 (C4 (Web Text))

Max Activating Token Index: 130

Text #6

Max Range: 1.5242. Min Range: -1.5242

Max Act: 1.2940. Min Act: -0.0000

Data Index: 1089926 (C4 (Web Text))

Max Activating Token Index: 233

Text #7

Max Range: 1.5242. Min Range: -1.5242

Max Act: 1.3578. Min Act: -0.0000

Data Index: 1299610 (C4 (Web Text))

Max Activating Token Index: 561

Text #8

Max Range: 1.5242. Min Range: -1.5242

Max Act: 1.3152. Min Act: -0.0000

Data Index: 115695 (C4 (Web Text))

Max Activating Token Index: 272

Text #9

Max Range: 1.5242. Min Range: -1.5242

Max Act: 1.4101. Min Act: -0.0000

Data Index: 798964 (C4 (Web Text))

Max Activating Token Index: 639

Text #10

Max Range: 1.5242. Min Range: -1.5242

Max Act: 1.2471. Min Act: -0.0000

Data Index: 1091312 (C4 (Web Text))

Max Activating Token Index: 204

Text #11

Max Range: 1.5242. Min Range: -1.5242

Max Act: 1.3062. Min Act: -0.0000

Data Index: 298926 (C4 (Web Text))

Max Activating Token Index: 839

Text #12

Max Range: 1.5242. Min Range: -1.5242

Max Act: 1.2158. Min Act: -0.0000

Data Index: 1175638 (C4 (Web Text))

Max Activating Token Index: 728

Text #13

Max Range: 1.5242. Min Range: -1.5242

Max Act: 1.2862. Min Act: -0.0000

Data Index: 632761 (C4 (Web Text))

Max Activating Token Index: 663

Text #14

Max Range: 1.5242. Min Range: -1.5242

Max Act: 1.2574. Min Act: -0.0000

Data Index: 973008 (C4 (Web Text))

Max Activating Token Index: 762

Text #15

Max Range: 1.5242. Min Range: -1.5242

Max Act: 1.2496. Min Act: -0.0000

Data Index: 824998 (C4 (Web Text))

Max Activating Token Index: 319

Text #16

Max Range: 1.5242. Min Range: -1.5242

Max Act: 1.2782. Min Act: -0.0000

Data Index: 84335 (C4 (Web Text))

Max Activating Token Index: 224

Text #17

Max Range: 1.5242. Min Range: -1.5242

Max Act: 1.1580. Min Act: -0.0000

Data Index: 406808 (C4 (Web Text))

Max Activating Token Index: 754

Text #18

Max Range: 1.5242. Min Range: -1.5242

Max Act: 1.2294. Min Act: -0.0000

Data Index: 1072888 (C4 (Web Text))

Max Activating Token Index: 459

Text #19

Max Range: 1.5242. Min Range: -1.5242

Max Act: 1.1835. Min Act: -0.0000

Data Index: 929762 (C4 (Web Text))

Max Activating Token Index: 155