Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 2693 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 1.5109. Min Range: -1.5109

Max Act: 1.5109. Min Act: -0.0000

Data Index: 953943 (C4 (Web Text))

Max Activating Token Index: 899

Text #1

Max Range: 1.5109. Min Range: -1.5109

Max Act: 0.6264. Min Act: -0.0000

Data Index: 83284 (C4 (Web Text))

Max Activating Token Index: 962

Text #2

Max Range: 1.5109. Min Range: -1.5109

Max Act: 0.5826. Min Act: -0.0000

Data Index: 251955 (C4 (Web Text))

Max Activating Token Index: 1015

Text #3

Max Range: 1.5109. Min Range: -1.5109

Max Act: 0.5907. Min Act: -0.0000

Data Index: 1052481 (C4 (Web Text))

Max Activating Token Index: 376

Text #4

Max Range: 1.5109. Min Range: -1.5109

Max Act: 0.5704. Min Act: -0.0000

Data Index: 560660 (C4 (Web Text))

Max Activating Token Index: 437

Text #5

Max Range: 1.5109. Min Range: -1.5109

Max Act: 0.5660. Min Act: 0.0001

Data Index: 1162496 (C4 (Web Text))

Max Activating Token Index: 705

Text #6

Max Range: 1.5109. Min Range: -1.5109

Max Act: 0.5882. Min Act: 0.0000

Data Index: 913008 (C4 (Web Text))

Max Activating Token Index: 800

Text #7

Max Range: 1.5109. Min Range: -1.5109

Max Act: 0.5330. Min Act: -0.0000

Data Index: 1248040 (C4 (Web Text))

Max Activating Token Index: 265

Text #8

Max Range: 1.5109. Min Range: -1.5109

Max Act: 0.5221. Min Act: 0.0001

Data Index: 395195 (C4 (Web Text))

Max Activating Token Index: 812

Text #9

Max Range: 1.5109. Min Range: -1.5109

Max Act: 0.5017. Min Act: -0.0000

Data Index: 404147 (C4 (Web Text))

Max Activating Token Index: 646

Text #10

Max Range: 1.5109. Min Range: -1.5109

Max Act: 0.5114. Min Act: -0.0000

Data Index: 162504 (C4 (Web Text))

Max Activating Token Index: 191

Text #11

Max Range: 1.5109. Min Range: -1.5109

Max Act: 0.5092. Min Act: -0.0000

Data Index: 1139957 (C4 (Web Text))

Max Activating Token Index: 361

Text #12

Max Range: 1.5109. Min Range: -1.5109

Max Act: 0.4899. Min Act: -0.0000

Data Index: 425691 (C4 (Web Text))

Max Activating Token Index: 949

Text #13

Max Range: 1.5109. Min Range: -1.5109

Max Act: 0.5026. Min Act: -0.0000

Data Index: 322818 (C4 (Web Text))

Max Activating Token Index: 29

Text #14

Max Range: 1.5109. Min Range: -1.5109

Max Act: 0.5114. Min Act: -0.0000

Data Index: 296295 (C4 (Web Text))

Max Activating Token Index: 753

Text #15

Max Range: 1.5109. Min Range: -1.5109

Max Act: 0.4869. Min Act: 0.0001

Data Index: 738486 (C4 (Web Text))

Max Activating Token Index: 44

Text #16

Max Range: 1.5109. Min Range: -1.5109

Max Act: 0.4992. Min Act: -0.0000

Data Index: 1217757 (C4 (Web Text))

Max Activating Token Index: 899

Text #17

Max Range: 1.5109. Min Range: -1.5109

Max Act: 0.5072. Min Act: -0.0000

Data Index: 1332954 (C4 (Web Text))

Max Activating Token Index: 775

Text #18

Max Range: 1.5109. Min Range: -1.5109

Max Act: 0.4585. Min Act: -0.0000

Data Index: 53397 (C4 (Web Text))

Max Activating Token Index: 454

Text #19

Max Range: 1.5109. Min Range: -1.5109

Max Act: 0.4346. Min Act: -0.0000

Data Index: 1159964 (C4 (Web Text))

Max Activating Token Index: 711