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

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

Neuron 3373 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: 2.7298. Min Range: -2.7298

Max Act: 2.7298. Min Act: -0.0000

Data Index: 81225 (C4 (Web Text))

Max Activating Token Index: 615

Text #1

Max Range: 2.7298. Min Range: -2.7298

Max Act: 2.6501. Min Act: -0.0000

Data Index: 430314 (C4 (Web Text))

Max Activating Token Index: 114

Text #2

Max Range: 2.7298. Min Range: -2.7298

Max Act: 2.3789. Min Act: -0.0000

Data Index: 133131 (C4 (Web Text))

Max Activating Token Index: 49

Text #3

Max Range: 2.7298. Min Range: -2.7298

Max Act: 2.4238. Min Act: -0.0001

Data Index: 568292 (C4 (Web Text))

Max Activating Token Index: 978

Text #4

Max Range: 2.7298. Min Range: -2.7298

Max Act: 2.2254. Min Act: -0.0000

Data Index: 928793 (C4 (Web Text))

Max Activating Token Index: 513

Text #5

Max Range: 2.7298. Min Range: -2.7298

Max Act: 2.0486. Min Act: -0.0000

Data Index: 843344 (C4 (Web Text))

Max Activating Token Index: 118

Text #6

Max Range: 2.7298. Min Range: -2.7298

Max Act: 2.3213. Min Act: -0.0000

Data Index: 243333 (C4 (Web Text))

Max Activating Token Index: 749

Text #7

Max Range: 2.7298. Min Range: -2.7298

Max Act: 1.9200. Min Act: -0.0001

Data Index: 766315 (C4 (Web Text))

Max Activating Token Index: 733

Text #8

Max Range: 2.7298. Min Range: -2.7298

Max Act: 2.0167. Min Act: -0.0001

Data Index: 800298 (C4 (Web Text))

Max Activating Token Index: 465

Text #9

Max Range: 2.7298. Min Range: -2.7298

Max Act: 1.9020. Min Act: -0.0000

Data Index: 211149 (C4 (Web Text))

Max Activating Token Index: 363

Text #10

Max Range: 2.7298. Min Range: -2.7298

Max Act: 1.9527. Min Act: -0.0000

Data Index: 713250 (C4 (Web Text))

Max Activating Token Index: 346

Text #11

Max Range: 2.7298. Min Range: -2.7298

Max Act: 2.0598. Min Act: -0.0001

Data Index: 541605 (C4 (Web Text))

Max Activating Token Index: 546

Text #12

Max Range: 2.7298. Min Range: -2.7298

Max Act: 1.8963. Min Act: -0.0001

Data Index: 935956 (C4 (Web Text))

Max Activating Token Index: 913

Text #13

Max Range: 2.7298. Min Range: -2.7298

Max Act: 1.8614. Min Act: -0.0000

Data Index: 751885 (C4 (Web Text))

Max Activating Token Index: 103

Text #14

Max Range: 2.7298. Min Range: -2.7298

Max Act: 1.9303. Min Act: -0.0001

Data Index: 1341985 (C4 (Web Text))

Max Activating Token Index: 564

Text #15

Max Range: 2.7298. Min Range: -2.7298

Max Act: 1.7110. Min Act: -0.0000

Data Index: 865201 (C4 (Web Text))

Max Activating Token Index: 587

Text #16

Max Range: 2.7298. Min Range: -2.7298

Max Act: 1.9153. Min Act: -0.0000

Data Index: 533084 (C4 (Web Text))

Max Activating Token Index: 537

Text #17

Max Range: 2.7298. Min Range: -2.7298

Max Act: 1.7930. Min Act: -0.0000

Data Index: 1182767 (C4 (Web Text))

Max Activating Token Index: 230

Text #18

Max Range: 2.7298. Min Range: -2.7298

Max Act: 1.6927. Min Act: -0.0000

Data Index: 812178 (C4 (Web Text))

Max Activating Token Index: 950

Text #19

Max Range: 2.7298. Min Range: -2.7298

Max Act: 1.6439. Min Act: -0.0001

Data Index: 455834 (C4 (Web Text))

Max Activating Token Index: 717