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

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

Neuron 3386 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.5689. Min Range: -1.5689

Max Act: 1.5461. Min Act: -0.0001

Data Index: 387060 (C4 (Web Text))

Max Activating Token Index: 51

Text #1

Max Range: 1.5689. Min Range: -1.5689

Max Act: 1.5689. Min Act: -0.0001

Data Index: 1152969 (C4 (Web Text))

Max Activating Token Index: 498

Text #2

Max Range: 1.5689. Min Range: -1.5689

Max Act: 1.4461. Min Act: -0.0001

Data Index: 921151 (C4 (Web Text))

Max Activating Token Index: 440

Text #3

Max Range: 1.5689. Min Range: -1.5689

Max Act: 1.4890. Min Act: -0.0001

Data Index: 1167057 (C4 (Web Text))

Max Activating Token Index: 513

Text #4

Max Range: 1.5689. Min Range: -1.5689

Max Act: 1.4069. Min Act: -0.0001

Data Index: 217010 (C4 (Web Text))

Max Activating Token Index: 308

Text #5

Max Range: 1.5689. Min Range: -1.5689

Max Act: 1.4286. Min Act: -0.0001

Data Index: 761499 (C4 (Web Text))

Max Activating Token Index: 956

Text #6

Max Range: 1.5689. Min Range: -1.5689

Max Act: 1.4855. Min Act: -0.0001

Data Index: 678810 (C4 (Web Text))

Max Activating Token Index: 193

Text #7

Max Range: 1.5689. Min Range: -1.5689

Max Act: 1.4022. Min Act: -0.0000

Data Index: 575462 (C4 (Web Text))

Max Activating Token Index: 798

Text #8

Max Range: 1.5689. Min Range: -1.5689

Max Act: 1.2399. Min Act: -0.0001

Data Index: 342973 (C4 (Web Text))

Max Activating Token Index: 312

Text #9

Max Range: 1.5689. Min Range: -1.5689

Max Act: 1.1700. Min Act: -0.0001

Data Index: 949487 (C4 (Web Text))

Max Activating Token Index: 725

Text #10

Max Range: 1.5689. Min Range: -1.5689

Max Act: 1.2841. Min Act: -0.0001

Data Index: 644548 (C4 (Web Text))

Max Activating Token Index: 201

Text #11

Max Range: 1.5689. Min Range: -1.5689

Max Act: 1.2706. Min Act: -0.0001

Data Index: 20302 (C4 (Web Text))

Max Activating Token Index: 192

Text #12

Max Range: 1.5689. Min Range: -1.5689

Max Act: 1.3368. Min Act: -0.0001

Data Index: 140825 (C4 (Web Text))

Max Activating Token Index: 62

Text #13

Max Range: 1.5689. Min Range: -1.5689

Max Act: 1.1949. Min Act: -0.0000

Data Index: 928877 (C4 (Web Text))

Max Activating Token Index: 265

Text #14

Max Range: 1.5689. Min Range: -1.5689

Max Act: 1.4036. Min Act: -0.0000

Data Index: 745431 (C4 (Web Text))

Max Activating Token Index: 343

Text #15

Max Range: 1.5689. Min Range: -1.5689

Max Act: 1.2855. Min Act: -0.0001

Data Index: 1237072 (C4 (Web Text))

Max Activating Token Index: 66

Text #16

Max Range: 1.5689. Min Range: -1.5689

Max Act: 1.3487. Min Act: -0.0000

Data Index: 725184 (C4 (Web Text))

Max Activating Token Index: 862

Text #17

Max Range: 1.5689. Min Range: -1.5689

Max Act: 1.1797. Min Act: -0.0000

Data Index: 284986 (C4 (Web Text))

Max Activating Token Index: 677

Text #18

Max Range: 1.5689. Min Range: -1.5689

Max Act: 1.3400. Min Act: -0.0001

Data Index: 281370 (C4 (Web Text))

Max Activating Token Index: 224

Text #19

Max Range: 1.5689. Min Range: -1.5689

Max Act: 1.2899. Min Act: -0.0001

Data Index: 1224676 (C4 (Web Text))

Max Activating Token Index: 340