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

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

Neuron 4731 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3269. Min Range: -0.3269

Max Act: 0.3269. Min Act: -0.0002

Data Index: 372322 (C4 (Web Text))

Max Activating Token Index: 380

Text #1

Max Range: 0.3269. Min Range: -0.3269

Max Act: 0.3221. Min Act: -0.0002

Data Index: 202960 (C4 (Web Text))

Max Activating Token Index: 235

Text #2

Max Range: 0.3269. Min Range: -0.3269

Max Act: 0.2892. Min Act: -0.0002

Data Index: 1268302 (C4 (Web Text))

Max Activating Token Index: 746

Text #3

Max Range: 0.3269. Min Range: -0.3269

Max Act: 0.2950. Min Act: -0.0002

Data Index: 547565 (C4 (Web Text))

Max Activating Token Index: 108

Text #4

Max Range: 0.3269. Min Range: -0.3269

Max Act: 0.2840. Min Act: -0.0002

Data Index: 716748 (C4 (Web Text))

Max Activating Token Index: 718

Text #5

Max Range: 0.3269. Min Range: -0.3269

Max Act: 0.2626. Min Act: -0.0002

Data Index: 1115730 (C4 (Web Text))

Max Activating Token Index: 295

Text #6

Max Range: 0.3269. Min Range: -0.3269

Max Act: 0.2605. Min Act: -0.0002

Data Index: 784682 (C4 (Web Text))

Max Activating Token Index: 197

Text #7

Max Range: 0.3269. Min Range: -0.3269

Max Act: 0.2717. Min Act: -0.0002

Data Index: 263851 (C4 (Web Text))

Max Activating Token Index: 822

Text #8

Max Range: 0.3269. Min Range: -0.3269

Max Act: 0.2648. Min Act: -0.0002

Data Index: 889847 (C4 (Web Text))

Max Activating Token Index: 116

Text #9

Max Range: 0.3269. Min Range: -0.3269

Max Act: 0.2626. Min Act: -0.0002

Data Index: 387465 (C4 (Web Text))

Max Activating Token Index: 57

Text #10

Max Range: 0.3269. Min Range: -0.3269

Max Act: 0.2603. Min Act: -0.0002

Data Index: 937911 (C4 (Web Text))

Max Activating Token Index: 634

Text #11

Max Range: 0.3269. Min Range: -0.3269

Max Act: 0.2576. Min Act: -0.0002

Data Index: 883992 (C4 (Web Text))

Max Activating Token Index: 598

Text #12

Max Range: 0.3269. Min Range: -0.3269

Max Act: 0.2537. Min Act: -0.0002

Data Index: 1013088 (C4 (Web Text))

Max Activating Token Index: 765

Text #13

Max Range: 0.3269. Min Range: -0.3269

Max Act: 0.2406. Min Act: -0.0002

Data Index: 1004673 (C4 (Web Text))

Max Activating Token Index: 356

Text #14

Max Range: 0.3269. Min Range: -0.3269

Max Act: 0.2520. Min Act: -0.0002

Data Index: 176994 (C4 (Web Text))

Max Activating Token Index: 497

Text #15

Max Range: 0.3269. Min Range: -0.3269

Max Act: 0.2351. Min Act: -0.0002

Data Index: 549021 (C4 (Web Text))

Max Activating Token Index: 238

Text #16

Max Range: 0.3269. Min Range: -0.3269

Max Act: 0.2433. Min Act: -0.0002

Data Index: 923069 (C4 (Web Text))

Max Activating Token Index: 210

Text #17

Max Range: 0.3269. Min Range: -0.3269

Max Act: 0.2435. Min Act: -0.0002

Data Index: 1070035 (C4 (Web Text))

Max Activating Token Index: 461

Text #18

Max Range: 0.3269. Min Range: -0.3269

Max Act: 0.2337. Min Act: -0.0002

Data Index: 511721 (C4 (Web Text))

Max Activating Token Index: 773

Text #19

Max Range: 0.3269. Min Range: -0.3269

Max Act: 0.2506. Min Act: -0.0002

Data Index: 559275 (C4 (Web Text))

Max Activating Token Index: 406