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

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

Neuron 5468 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.4064. Min Range: -1.4064

Max Act: 1.4064. Min Act: -0.0000

Data Index: 344411 (C4 (Web Text))

Max Activating Token Index: 500

Text #1

Max Range: 1.4064. Min Range: -1.4064

Max Act: 1.2899. Min Act: -0.0000

Data Index: 643669 (C4 (Web Text))

Max Activating Token Index: 837

Text #2

Max Range: 1.4064. Min Range: -1.4064

Max Act: 1.1349. Min Act: -0.0000

Data Index: 1169656 (C4 (Web Text))

Max Activating Token Index: 355

Text #3

Max Range: 1.4064. Min Range: -1.4064

Max Act: 1.0921. Min Act: -0.0000

Data Index: 939488 (C4 (Web Text))

Max Activating Token Index: 350

Text #4

Max Range: 1.4064. Min Range: -1.4064

Max Act: 1.2291. Min Act: -0.0000

Data Index: 262250 (C4 (Web Text))

Max Activating Token Index: 368

Text #5

Max Range: 1.4064. Min Range: -1.4064

Max Act: 1.1494. Min Act: -0.0000

Data Index: 242920 (C4 (Web Text))

Max Activating Token Index: 344

Text #6

Max Range: 1.4064. Min Range: -1.4064

Max Act: 1.1031. Min Act: -0.0000

Data Index: 1064567 (C4 (Web Text))

Max Activating Token Index: 438

Text #7

Max Range: 1.4064. Min Range: -1.4064

Max Act: 1.1061. Min Act: -0.0000

Data Index: 1028265 (C4 (Web Text))

Max Activating Token Index: 908

Text #8

Max Range: 1.4064. Min Range: -1.4064

Max Act: 1.0655. Min Act: -0.0000

Data Index: 1019436 (C4 (Web Text))

Max Activating Token Index: 862

Text #9

Max Range: 1.4064. Min Range: -1.4064

Max Act: 1.0509. Min Act: -0.0000

Data Index: 295044 (C4 (Web Text))

Max Activating Token Index: 305

Text #10

Max Range: 1.4064. Min Range: -1.4064

Max Act: 0.9828. Min Act: -0.0000

Data Index: 227522 (C4 (Web Text))

Max Activating Token Index: 414

Text #11

Max Range: 1.4064. Min Range: -1.4064

Max Act: 1.0458. Min Act: -0.0000

Data Index: 686395 (C4 (Web Text))

Max Activating Token Index: 900

Text #12

Max Range: 1.4064. Min Range: -1.4064

Max Act: 1.0348. Min Act: -0.0000

Data Index: 1312670 (C4 (Web Text))

Max Activating Token Index: 161

Text #13

Max Range: 1.4064. Min Range: -1.4064

Max Act: 1.0261. Min Act: -0.0000

Data Index: 345085 (C4 (Web Text))

Max Activating Token Index: 109

Text #14

Max Range: 1.4064. Min Range: -1.4064

Max Act: 0.9926. Min Act: -0.0000

Data Index: 110004 (C4 (Web Text))

Max Activating Token Index: 672

Text #15

Max Range: 1.4064. Min Range: -1.4064

Max Act: 1.0111. Min Act: -0.0000

Data Index: 619086 (C4 (Web Text))

Max Activating Token Index: 642

Text #16

Max Range: 1.4064. Min Range: -1.4064

Max Act: 0.9817. Min Act: -0.0000

Data Index: 1010445 (C4 (Web Text))

Max Activating Token Index: 322

Text #17

Max Range: 1.4064. Min Range: -1.4064

Max Act: 0.9286. Min Act: -0.0000

Data Index: 1265104 (C4 (Web Text))

Max Activating Token Index: 819

Text #18

Max Range: 1.4064. Min Range: -1.4064

Max Act: 0.9879. Min Act: -0.0000

Data Index: 843516 (C4 (Web Text))

Max Activating Token Index: 720

Text #19

Max Range: 1.4064. Min Range: -1.4064

Max Act: 0.9821. Min Act: -0.0000

Data Index: 685689 (C4 (Web Text))

Max Activating Token Index: 214