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

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

Neuron 3232 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4212. Min Range: -0.4212

Max Act: 0.4212. Min Act: -0.0000

Data Index: 815721 (C4 (Web Text))

Max Activating Token Index: 446

Text #1

Max Range: 0.4212. Min Range: -0.4212

Max Act: 0.4091. Min Act: -0.0000

Data Index: 1053373 (C4 (Web Text))

Max Activating Token Index: 30

Text #2

Max Range: 0.4212. Min Range: -0.4212

Max Act: 0.3781. Min Act: -0.0000

Data Index: 161773 (C4 (Web Text))

Max Activating Token Index: 976

Text #3

Max Range: 0.4212. Min Range: -0.4212

Max Act: 0.3403. Min Act: -0.0000

Data Index: 391228 (C4 (Web Text))

Max Activating Token Index: 648

Text #4

Max Range: 0.4212. Min Range: -0.4212

Max Act: 0.3269. Min Act: -0.0000

Data Index: 705847 (C4 (Web Text))

Max Activating Token Index: 418

Text #5

Max Range: 0.4212. Min Range: -0.4212

Max Act: 0.3062. Min Act: -0.0000

Data Index: 1247679 (C4 (Web Text))

Max Activating Token Index: 410

Text #6

Max Range: 0.4212. Min Range: -0.4212

Max Act: 0.3142. Min Act: 0.0000

Data Index: 204365 (C4 (Web Text))

Max Activating Token Index: 248

Text #7

Max Range: 0.4212. Min Range: -0.4212

Max Act: 0.3115. Min Act: -0.0000

Data Index: 1081836 (C4 (Web Text))

Max Activating Token Index: 250

Text #8

Max Range: 0.4212. Min Range: -0.4212

Max Act: 0.2982. Min Act: -0.0000

Data Index: 1321262 (C4 (Web Text))

Max Activating Token Index: 522

Text #9

Max Range: 0.4212. Min Range: -0.4212

Max Act: 0.3017. Min Act: -0.0000

Data Index: 1258161 (C4 (Web Text))

Max Activating Token Index: 962

Text #10

Max Range: 0.4212. Min Range: -0.4212

Max Act: 0.2951. Min Act: 0.0000

Data Index: 1145363 (C4 (Web Text))

Max Activating Token Index: 620

Text #11

Max Range: 0.4212. Min Range: -0.4212

Max Act: 0.2962. Min Act: -0.0000

Data Index: 121546 (C4 (Web Text))

Max Activating Token Index: 215

Text #12

Max Range: 0.4212. Min Range: -0.4212

Max Act: 0.2873. Min Act: -0.0000

Data Index: 443245 (C4 (Web Text))

Max Activating Token Index: 493

Text #13

Max Range: 0.4212. Min Range: -0.4212

Max Act: 0.2868. Min Act: -0.0000

Data Index: 144263 (C4 (Web Text))

Max Activating Token Index: 822

Text #14

Max Range: 0.4212. Min Range: -0.4212

Max Act: 0.2843. Min Act: -0.0000

Data Index: 444130 (C4 (Web Text))

Max Activating Token Index: 65

Text #15

Max Range: 0.4212. Min Range: -0.4212

Max Act: 0.2848. Min Act: -0.0000

Data Index: 821323 (C4 (Web Text))

Max Activating Token Index: 506

Text #16

Max Range: 0.4212. Min Range: -0.4212

Max Act: 0.2853. Min Act: 0.0000

Data Index: 747302 (C4 (Web Text))

Max Activating Token Index: 420

Text #17

Max Range: 0.4212. Min Range: -0.4212

Max Act: 0.2778. Min Act: -0.0000

Data Index: 1096008 (C4 (Web Text))

Max Activating Token Index: 905

Text #18

Max Range: 0.4212. Min Range: -0.4212

Max Act: 0.2840. Min Act: -0.0000

Data Index: 106821 (C4 (Web Text))

Max Activating Token Index: 167

Text #19

Max Range: 0.4212. Min Range: -0.4212

Max Act: 0.2803. Min Act: -0.0000

Data Index: 786779 (C4 (Web Text))

Max Activating Token Index: 704