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

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

Neuron 5102 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: 0.7168. Min Range: -0.7168

Max Act: 0.7168. Min Act: 0.0000

Data Index: 183789 (C4 (Web Text))

Max Activating Token Index: 953

Text #1

Max Range: 0.7168. Min Range: -0.7168

Max Act: 0.6722. Min Act: -0.0000

Data Index: 1061939 (C4 (Web Text))

Max Activating Token Index: 930

Text #2

Max Range: 0.7168. Min Range: -0.7168

Max Act: 0.6614. Min Act: -0.0000

Data Index: 1321900 (C4 (Web Text))

Max Activating Token Index: 423

Text #3

Max Range: 0.7168. Min Range: -0.7168

Max Act: 0.5881. Min Act: -0.0000

Data Index: 1171581 (C4 (Web Text))

Max Activating Token Index: 762

Text #4

Max Range: 0.7168. Min Range: -0.7168

Max Act: 0.4950. Min Act: 0.0001

Data Index: 1316019 (C4 (Web Text))

Max Activating Token Index: 142

Text #5

Max Range: 0.7168. Min Range: -0.7168

Max Act: 0.4824. Min Act: 0.0000

Data Index: 945545 (C4 (Web Text))

Max Activating Token Index: 78

Text #6

Max Range: 0.7168. Min Range: -0.7168

Max Act: 0.4674. Min Act: 0.0001

Data Index: 1242288 (C4 (Web Text))

Max Activating Token Index: 65

Text #7

Max Range: 0.7168. Min Range: -0.7168

Max Act: 0.4450. Min Act: -0.0000

Data Index: 825097 (C4 (Web Text))

Max Activating Token Index: 523

Text #8

Max Range: 0.7168. Min Range: -0.7168

Max Act: 0.4302. Min Act: 0.0000

Data Index: 274923 (C4 (Web Text))

Max Activating Token Index: 366

Text #9

Max Range: 0.7168. Min Range: -0.7168

Max Act: 0.4263. Min Act: 0.0001

Data Index: 225844 (C4 (Web Text))

Max Activating Token Index: 355

Text #10

Max Range: 0.7168. Min Range: -0.7168

Max Act: 0.3930. Min Act: 0.0001

Data Index: 955470 (C4 (Web Text))

Max Activating Token Index: 818

Text #11

Max Range: 0.7168. Min Range: -0.7168

Max Act: 0.3896. Min Act: -0.0000

Data Index: 338399 (C4 (Web Text))

Max Activating Token Index: 399

Text #12

Max Range: 0.7168. Min Range: -0.7168

Max Act: 0.4112. Min Act: 0.0000

Data Index: 862910 (C4 (Web Text))

Max Activating Token Index: 784

Text #13

Max Range: 0.7168. Min Range: -0.7168

Max Act: 0.4063. Min Act: -0.0000

Data Index: 362024 (C4 (Web Text))

Max Activating Token Index: 257

Text #14

Max Range: 0.7168. Min Range: -0.7168

Max Act: 0.4264. Min Act: 0.0000

Data Index: 1244138 (C4 (Web Text))

Max Activating Token Index: 557

Text #15

Max Range: 0.7168. Min Range: -0.7168

Max Act: 0.3973. Min Act: -0.0000

Data Index: 26020 (C4 (Web Text))

Max Activating Token Index: 1014

Text #16

Max Range: 0.7168. Min Range: -0.7168

Max Act: 0.3868. Min Act: -0.0000

Data Index: 628522 (C4 (Web Text))

Max Activating Token Index: 532

Text #17

Max Range: 0.7168. Min Range: -0.7168

Max Act: 0.3856. Min Act: -0.0000

Data Index: 726058 (C4 (Web Text))

Max Activating Token Index: 568

Text #18

Max Range: 0.7168. Min Range: -0.7168

Max Act: 0.3961. Min Act: -0.0000

Data Index: 711035 (C4 (Web Text))

Max Activating Token Index: 882

Text #19

Max Range: 0.7168. Min Range: -0.7168

Max Act: 0.3792. Min Act: -0.0000

Data Index: 659204 (C4 (Web Text))

Max Activating Token Index: 574