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

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

Neuron 2959 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.1633. Min Range: -1.1633

Max Act: 1.1633. Min Act: -0.0003

Data Index: 236217 (C4 (Web Text))

Max Activating Token Index: 763

Text #1

Max Range: 1.1633. Min Range: -1.1633

Max Act: 1.0574. Min Act: -0.0003

Data Index: 404963 (C4 (Web Text))

Max Activating Token Index: 300

Text #2

Max Range: 1.1633. Min Range: -1.1633

Max Act: 1.1062. Min Act: -0.0003

Data Index: 1167937 (C4 (Web Text))

Max Activating Token Index: 129

Text #3

Max Range: 1.1633. Min Range: -1.1633

Max Act: 1.0500. Min Act: -0.0002

Data Index: 844167 (C4 (Web Text))

Max Activating Token Index: 222

Text #4

Max Range: 1.1633. Min Range: -1.1633

Max Act: 1.0175. Min Act: -0.0003

Data Index: 316948 (C4 (Web Text))

Max Activating Token Index: 702

Text #5

Max Range: 1.1633. Min Range: -1.1633

Max Act: 1.0168. Min Act: -0.0003

Data Index: 539381 (C4 (Web Text))

Max Activating Token Index: 473

Text #6

Max Range: 1.1633. Min Range: -1.1633

Max Act: 0.9456. Min Act: -0.0003

Data Index: 83069 (C4 (Web Text))

Max Activating Token Index: 238

Text #7

Max Range: 1.1633. Min Range: -1.1633

Max Act: 0.9440. Min Act: -0.0003

Data Index: 723614 (C4 (Web Text))

Max Activating Token Index: 149

Text #8

Max Range: 1.1633. Min Range: -1.1633

Max Act: 0.9335. Min Act: -0.0003

Data Index: 70710 (C4 (Web Text))

Max Activating Token Index: 195

Text #9

Max Range: 1.1633. Min Range: -1.1633

Max Act: 0.9662. Min Act: -0.0003

Data Index: 637839 (C4 (Web Text))

Max Activating Token Index: 919

Text #10

Max Range: 1.1633. Min Range: -1.1633

Max Act: 0.8996. Min Act: -0.0003

Data Index: 1144041 (C4 (Web Text))

Max Activating Token Index: 875

Text #11

Max Range: 1.1633. Min Range: -1.1633

Max Act: 0.9558. Min Act: -0.0003

Data Index: 1233703 (C4 (Web Text))

Max Activating Token Index: 302

Text #12

Max Range: 1.1633. Min Range: -1.1633

Max Act: 0.9541. Min Act: -0.0003

Data Index: 777232 (C4 (Web Text))

Max Activating Token Index: 726

Text #13

Max Range: 1.1633. Min Range: -1.1633

Max Act: 0.9458. Min Act: -0.0003

Data Index: 679053 (C4 (Web Text))

Max Activating Token Index: 102

Text #14

Max Range: 1.1633. Min Range: -1.1633

Max Act: 0.9276. Min Act: -0.0003

Data Index: 1080317 (C4 (Web Text))

Max Activating Token Index: 773

Text #15

Max Range: 1.1633. Min Range: -1.1633

Max Act: 0.9272. Min Act: -0.0003

Data Index: 156579 (C4 (Web Text))

Max Activating Token Index: 1013

Text #16

Max Range: 1.1633. Min Range: -1.1633

Max Act: 0.9238. Min Act: -0.0003

Data Index: 442822 (C4 (Web Text))

Max Activating Token Index: 164

Text #17

Max Range: 1.1633. Min Range: -1.1633

Max Act: 0.9248. Min Act: -0.0003

Data Index: 355560 (C4 (Web Text))

Max Activating Token Index: 191

Text #18

Max Range: 1.1633. Min Range: -1.1633

Max Act: 0.9213. Min Act: -0.0003

Data Index: 221754 (C4 (Web Text))

Max Activating Token Index: 10

Text #19

Max Range: 1.1633. Min Range: -1.1633

Max Act: 0.9150. Min Act: -0.0003

Data Index: 126786 (C4 (Web Text))

Max Activating Token Index: 696