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

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

Neuron 2528 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.6622. Min Range: -1.6622

Max Act: 1.6509. Min Act: -0.0001

Data Index: 485527 (C4 (Web Text))

Max Activating Token Index: 746

Text #1

Max Range: 1.6622. Min Range: -1.6622

Max Act: 1.6622. Min Act: -0.0000

Data Index: 1154461 (C4 (Web Text))

Max Activating Token Index: 179

Text #2

Max Range: 1.6622. Min Range: -1.6622

Max Act: 1.2461. Min Act: -0.0000

Data Index: 559416 (C4 (Web Text))

Max Activating Token Index: 198

Text #3

Max Range: 1.6622. Min Range: -1.6622

Max Act: 1.1272. Min Act: -0.0001

Data Index: 1047199 (C4 (Web Text))

Max Activating Token Index: 843

Text #4

Max Range: 1.6622. Min Range: -1.6622

Max Act: 1.1254. Min Act: -0.0001

Data Index: 683388 (C4 (Web Text))

Max Activating Token Index: 784

Text #5

Max Range: 1.6622. Min Range: -1.6622

Max Act: 1.0338. Min Act: -0.0001

Data Index: 942359 (C4 (Web Text))

Max Activating Token Index: 972

Text #6

Max Range: 1.6622. Min Range: -1.6622

Max Act: 1.1350. Min Act: -0.0001

Data Index: 538948 (C4 (Web Text))

Max Activating Token Index: 837

Text #7

Max Range: 1.6622. Min Range: -1.6622

Max Act: 0.9942. Min Act: -0.0000

Data Index: 906217 (C4 (Web Text))

Max Activating Token Index: 473

Text #8

Max Range: 1.6622. Min Range: -1.6622

Max Act: 0.9832. Min Act: -0.0001

Data Index: 908023 (C4 (Web Text))

Max Activating Token Index: 342

Text #9

Max Range: 1.6622. Min Range: -1.6622

Max Act: 1.0464. Min Act: -0.0001

Data Index: 389181 (C4 (Web Text))

Max Activating Token Index: 774

Text #10

Max Range: 1.6622. Min Range: -1.6622

Max Act: 0.8981. Min Act: -0.0001

Data Index: 147234 (C4 (Web Text))

Max Activating Token Index: 387

Text #11

Max Range: 1.6622. Min Range: -1.6622

Max Act: 0.8986. Min Act: -0.0001

Data Index: 1002405 (C4 (Web Text))

Max Activating Token Index: 588

Text #12

Max Range: 1.6622. Min Range: -1.6622

Max Act: 0.8726. Min Act: -0.0001

Data Index: 1288197 (C4 (Web Text))

Max Activating Token Index: 953

Text #13

Max Range: 1.6622. Min Range: -1.6622

Max Act: 0.8854. Min Act: -0.0000

Data Index: 1067898 (C4 (Web Text))

Max Activating Token Index: 116

Text #14

Max Range: 1.6622. Min Range: -1.6622

Max Act: 0.8722. Min Act: -0.0000

Data Index: 840310 (C4 (Web Text))

Max Activating Token Index: 646

Text #15

Max Range: 1.6622. Min Range: -1.6622

Max Act: 0.8730. Min Act: -0.0001

Data Index: 762820 (C4 (Web Text))

Max Activating Token Index: 805

Text #16

Max Range: 1.6622. Min Range: -1.6622

Max Act: 0.7333. Min Act: -0.0001

Data Index: 1219489 (C4 (Web Text))

Max Activating Token Index: 106

Text #17

Max Range: 1.6622. Min Range: -1.6622

Max Act: 0.8265. Min Act: -0.0000

Data Index: 87229 (C4 (Web Text))

Max Activating Token Index: 397

Text #18

Max Range: 1.6622. Min Range: -1.6622

Max Act: 0.8223. Min Act: -0.0001

Data Index: 4351 (C4 (Web Text))

Max Activating Token Index: 565

Text #19

Max Range: 1.6622. Min Range: -1.6622

Max Act: 0.7945. Min Act: -0.0001

Data Index: 93632 (C4 (Web Text))

Max Activating Token Index: 371