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

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

Neuron 49 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2168. Min Range: -0.2168

Max Act: 0.2150. Min Act: -0.0000

Data Index: 1636210 (Python Code)

Max Activating Token Index: 91

Text #1

Max Range: 0.2168. Min Range: -0.2168

Max Act: 0.2168. Min Act: -0.0000

Data Index: 1055654 (C4 (Web Text))

Max Activating Token Index: 447

Text #2

Max Range: 0.2168. Min Range: -0.2168

Max Act: 0.1956. Min Act: -0.0000

Data Index: 488942 (C4 (Web Text))

Max Activating Token Index: 704

Text #3

Max Range: 0.2168. Min Range: -0.2168

Max Act: 0.1953. Min Act: -0.0000

Data Index: 432043 (C4 (Web Text))

Max Activating Token Index: 74

Text #4

Max Range: 0.2168. Min Range: -0.2168

Max Act: 0.1890. Min Act: -0.0000

Data Index: 1453967 (Python Code)

Max Activating Token Index: 841

Text #5

Max Range: 0.2168. Min Range: -0.2168

Max Act: 0.1935. Min Act: -0.0000

Data Index: 961939 (C4 (Web Text))

Max Activating Token Index: 269

Text #6

Max Range: 0.2168. Min Range: -0.2168

Max Act: 0.1918. Min Act: -0.0000

Data Index: 411356 (C4 (Web Text))

Max Activating Token Index: 90

Text #7

Max Range: 0.2168. Min Range: -0.2168

Max Act: 0.1881. Min Act: -0.0000

Data Index: 40962 (C4 (Web Text))

Max Activating Token Index: 114

Text #8

Max Range: 0.2168. Min Range: -0.2168

Max Act: 0.1871. Min Act: -0.0000

Data Index: 296706 (C4 (Web Text))

Max Activating Token Index: 228

Text #9

Max Range: 0.2168. Min Range: -0.2168

Max Act: 0.1841. Min Act: -0.0000

Data Index: 592424 (C4 (Web Text))

Max Activating Token Index: 93

Text #10

Max Range: 0.2168. Min Range: -0.2168

Max Act: 0.1830. Min Act: -0.0000

Data Index: 961067 (C4 (Web Text))

Max Activating Token Index: 61

Text #11

Max Range: 0.2168. Min Range: -0.2168

Max Act: 0.1806. Min Act: -0.0000

Data Index: 490877 (C4 (Web Text))

Max Activating Token Index: 803

Text #12

Max Range: 0.2168. Min Range: -0.2168

Max Act: 0.1864. Min Act: -0.0000

Data Index: 927558 (C4 (Web Text))

Max Activating Token Index: 569

Text #13

Max Range: 0.2168. Min Range: -0.2168

Max Act: 0.1781. Min Act: -0.0000

Data Index: 599447 (C4 (Web Text))

Max Activating Token Index: 33

Text #14

Max Range: 0.2168. Min Range: -0.2168

Max Act: 0.1844. Min Act: -0.0000

Data Index: 697631 (C4 (Web Text))

Max Activating Token Index: 287

Text #15

Max Range: 0.2168. Min Range: -0.2168

Max Act: 0.1822. Min Act: -0.0000

Data Index: 1315581 (C4 (Web Text))

Max Activating Token Index: 464

Text #16

Max Range: 0.2168. Min Range: -0.2168

Max Act: 0.1766. Min Act: -0.0000

Data Index: 519138 (C4 (Web Text))

Max Activating Token Index: 33

Text #17

Max Range: 0.2168. Min Range: -0.2168

Max Act: 0.1817. Min Act: -0.0000

Data Index: 1026054 (C4 (Web Text))

Max Activating Token Index: 891

Text #18

Max Range: 0.2168. Min Range: -0.2168

Max Act: 0.1754. Min Act: -0.0000

Data Index: 723592 (C4 (Web Text))

Max Activating Token Index: 223

Text #19

Max Range: 0.2168. Min Range: -0.2168

Max Act: 0.1681. Min Act: -0.0000

Data Index: 772828 (C4 (Web Text))

Max Activating Token Index: 184