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

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

Neuron 5476 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 1.7850. Min Range: -1.7850

Max Act: 1.7850. Min Act: -0.0000

Data Index: 799312 (C4 (Web Text))

Max Activating Token Index: 892

Text #1

Max Range: 1.7850. Min Range: -1.7850

Max Act: 1.4993. Min Act: -0.0000

Data Index: 1020050 (C4 (Web Text))

Max Activating Token Index: 655

Text #2

Max Range: 1.7850. Min Range: -1.7850

Max Act: 1.4026. Min Act: 0.0000

Data Index: 293254 (C4 (Web Text))

Max Activating Token Index: 232

Text #3

Max Range: 1.7850. Min Range: -1.7850

Max Act: 1.5013. Min Act: -0.0000

Data Index: 409335 (C4 (Web Text))

Max Activating Token Index: 962

Text #4

Max Range: 1.7850. Min Range: -1.7850

Max Act: 1.3066. Min Act: -0.0000

Data Index: 384991 (C4 (Web Text))

Max Activating Token Index: 407

Text #5

Max Range: 1.7850. Min Range: -1.7850

Max Act: 1.2061. Min Act: -0.0000

Data Index: 1342056 (C4 (Web Text))

Max Activating Token Index: 276

Text #6

Max Range: 1.7850. Min Range: -1.7850

Max Act: 1.2595. Min Act: -0.0000

Data Index: 320856 (C4 (Web Text))

Max Activating Token Index: 1010

Text #7

Max Range: 1.7850. Min Range: -1.7850

Max Act: 1.3091. Min Act: -0.0000

Data Index: 1199777 (C4 (Web Text))

Max Activating Token Index: 635

Text #8

Max Range: 1.7850. Min Range: -1.7850

Max Act: 1.2855. Min Act: -0.0000

Data Index: 427464 (C4 (Web Text))

Max Activating Token Index: 558

Text #9

Max Range: 1.7850. Min Range: -1.7850

Max Act: 1.2912. Min Act: -0.0000

Data Index: 242889 (C4 (Web Text))

Max Activating Token Index: 880

Text #10

Max Range: 1.7850. Min Range: -1.7850

Max Act: 1.2119. Min Act: -0.0000

Data Index: 396030 (C4 (Web Text))

Max Activating Token Index: 196

Text #11

Max Range: 1.7850. Min Range: -1.7850

Max Act: 1.2379. Min Act: -0.0000

Data Index: 175029 (C4 (Web Text))

Max Activating Token Index: 637

Text #12

Max Range: 1.7850. Min Range: -1.7850

Max Act: 1.2094. Min Act: -0.0000

Data Index: 1109444 (C4 (Web Text))

Max Activating Token Index: 959

Text #13

Max Range: 1.7850. Min Range: -1.7850

Max Act: 1.1874. Min Act: -0.0000

Data Index: 296351 (C4 (Web Text))

Max Activating Token Index: 445

Text #14

Max Range: 1.7850. Min Range: -1.7850

Max Act: 1.2526. Min Act: -0.0000

Data Index: 751493 (C4 (Web Text))

Max Activating Token Index: 405

Text #15

Max Range: 1.7850. Min Range: -1.7850

Max Act: 1.1860. Min Act: -0.0000

Data Index: 937942 (C4 (Web Text))

Max Activating Token Index: 1016

Text #16

Max Range: 1.7850. Min Range: -1.7850

Max Act: 1.1731. Min Act: -0.0000

Data Index: 349023 (C4 (Web Text))

Max Activating Token Index: 969

Text #17

Max Range: 1.7850. Min Range: -1.7850

Max Act: 1.1660. Min Act: -0.0000

Data Index: 757751 (C4 (Web Text))

Max Activating Token Index: 853

Text #18

Max Range: 1.7850. Min Range: -1.7850

Max Act: 1.1232. Min Act: -0.0000

Data Index: 795849 (C4 (Web Text))

Max Activating Token Index: 313

Text #19

Max Range: 1.7850. Min Range: -1.7850

Max Act: 1.1209. Min Act: -0.0000

Data Index: 111710 (C4 (Web Text))

Max Activating Token Index: 406