Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 420 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.1299. Min Range: -0.1299

Max Act: 0.1299. Min Act: -0.0001

Data Index: 880723 (C4 (Web Text))

Max Activating Token Index: 888

Text #1

Max Range: 0.1299. Min Range: -0.1299

Max Act: 0.1224. Min Act: -0.0001

Data Index: 941757 (C4 (Web Text))

Max Activating Token Index: 658

Text #2

Max Range: 0.1299. Min Range: -0.1299

Max Act: 0.1219. Min Act: -0.0001

Data Index: 1020521 (C4 (Web Text))

Max Activating Token Index: 701

Text #3

Max Range: 0.1299. Min Range: -0.1299

Max Act: 0.1260. Min Act: -0.0001

Data Index: 1311834 (C4 (Web Text))

Max Activating Token Index: 641

Text #4

Max Range: 0.1299. Min Range: -0.1299

Max Act: 0.1111. Min Act: -0.0001

Data Index: 939370 (C4 (Web Text))

Max Activating Token Index: 892

Text #5

Max Range: 0.1299. Min Range: -0.1299

Max Act: 0.1024. Min Act: -0.0001

Data Index: 976074 (C4 (Web Text))

Max Activating Token Index: 177

Text #6

Max Range: 0.1299. Min Range: -0.1299

Max Act: 0.0981. Min Act: -0.0001

Data Index: 306470 (C4 (Web Text))

Max Activating Token Index: 803

Text #7

Max Range: 0.1299. Min Range: -0.1299

Max Act: 0.1018. Min Act: -0.0001

Data Index: 1230253 (C4 (Web Text))

Max Activating Token Index: 639

Text #8

Max Range: 0.1299. Min Range: -0.1299

Max Act: 0.0957. Min Act: -0.0001

Data Index: 1041821 (C4 (Web Text))

Max Activating Token Index: 428

Text #9

Max Range: 0.1299. Min Range: -0.1299

Max Act: 0.0990. Min Act: -0.0001

Data Index: 689009 (C4 (Web Text))

Max Activating Token Index: 521

Text #10

Max Range: 0.1299. Min Range: -0.1299

Max Act: 0.0855. Min Act: -0.0001

Data Index: 280298 (C4 (Web Text))

Max Activating Token Index: 146

Text #11

Max Range: 0.1299. Min Range: -0.1299

Max Act: 0.0837. Min Act: -0.0001

Data Index: 138593 (C4 (Web Text))

Max Activating Token Index: 396

Text #12

Max Range: 0.1299. Min Range: -0.1299

Max Act: 0.0844. Min Act: -0.0001

Data Index: 180718 (C4 (Web Text))

Max Activating Token Index: 280

Text #13

Max Range: 0.1299. Min Range: -0.1299

Max Act: 0.0835. Min Act: -0.0001

Data Index: 381096 (C4 (Web Text))

Max Activating Token Index: 390

Text #14

Max Range: 0.1299. Min Range: -0.1299

Max Act: 0.0816. Min Act: -0.0001

Data Index: 1359438 (C4 (Web Text))

Max Activating Token Index: 174

Text #15

Max Range: 0.1299. Min Range: -0.1299

Max Act: 0.0787. Min Act: -0.0001

Data Index: 618303 (C4 (Web Text))

Max Activating Token Index: 762

Text #16

Max Range: 0.1299. Min Range: -0.1299

Max Act: 0.0743. Min Act: -0.0001

Data Index: 592902 (C4 (Web Text))

Max Activating Token Index: 183

Text #17

Max Range: 0.1299. Min Range: -0.1299

Max Act: 0.0771. Min Act: -0.0001

Data Index: 873261 (C4 (Web Text))

Max Activating Token Index: 808

Text #18

Max Range: 0.1299. Min Range: -0.1299

Max Act: 0.0814. Min Act: -0.0001

Data Index: 256898 (C4 (Web Text))

Max Activating Token Index: 195

Text #19

Max Range: 0.1299. Min Range: -0.1299

Max Act: 0.0757. Min Act: -0.0001

Data Index: 425522 (C4 (Web Text))

Max Activating Token Index: 26