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

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

Neuron 3978 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0849. Min Range: -1.0849

Max Act: 1.0822. Min Act: -0.0001

Data Index: 900267 (C4 (Web Text))

Max Activating Token Index: 390

Text #1

Max Range: 1.0849. Min Range: -1.0849

Max Act: 0.9825. Min Act: -0.0001

Data Index: 566352 (C4 (Web Text))

Max Activating Token Index: 636

Text #2

Max Range: 1.0849. Min Range: -1.0849

Max Act: 1.0307. Min Act: -0.0001

Data Index: 640131 (C4 (Web Text))

Max Activating Token Index: 397

Text #3

Max Range: 1.0849. Min Range: -1.0849

Max Act: 1.0849. Min Act: -0.0001

Data Index: 611150 (C4 (Web Text))

Max Activating Token Index: 970

Text #4

Max Range: 1.0849. Min Range: -1.0849

Max Act: 1.0376. Min Act: -0.0001

Data Index: 1206908 (C4 (Web Text))

Max Activating Token Index: 330

Text #5

Max Range: 1.0849. Min Range: -1.0849

Max Act: 0.9771. Min Act: -0.0001

Data Index: 135298 (C4 (Web Text))

Max Activating Token Index: 865

Text #6

Max Range: 1.0849. Min Range: -1.0849

Max Act: 1.0355. Min Act: -0.0001

Data Index: 765036 (C4 (Web Text))

Max Activating Token Index: 974

Text #7

Max Range: 1.0849. Min Range: -1.0849

Max Act: 0.9431. Min Act: -0.0001

Data Index: 136343 (C4 (Web Text))

Max Activating Token Index: 480

Text #8

Max Range: 1.0849. Min Range: -1.0849

Max Act: 0.9721. Min Act: -0.0001

Data Index: 547261 (C4 (Web Text))

Max Activating Token Index: 916

Text #9

Max Range: 1.0849. Min Range: -1.0849

Max Act: 0.9311. Min Act: -0.0001

Data Index: 1308514 (C4 (Web Text))

Max Activating Token Index: 82

Text #10

Max Range: 1.0849. Min Range: -1.0849

Max Act: 0.9389. Min Act: -0.0001

Data Index: 1209319 (C4 (Web Text))

Max Activating Token Index: 714

Text #11

Max Range: 1.0849. Min Range: -1.0849

Max Act: 0.8950. Min Act: -0.0001

Data Index: 1078537 (C4 (Web Text))

Max Activating Token Index: 232

Text #12

Max Range: 1.0849. Min Range: -1.0849

Max Act: 0.8447. Min Act: -0.0001

Data Index: 570476 (C4 (Web Text))

Max Activating Token Index: 786

Text #13

Max Range: 1.0849. Min Range: -1.0849

Max Act: 0.6943. Min Act: -0.0001

Data Index: 73751 (C4 (Web Text))

Max Activating Token Index: 324

Text #14

Max Range: 1.0849. Min Range: -1.0849

Max Act: 0.9081. Min Act: -0.0001

Data Index: 700098 (C4 (Web Text))

Max Activating Token Index: 704

Text #15

Max Range: 1.0849. Min Range: -1.0849

Max Act: 0.8653. Min Act: -0.0001

Data Index: 908592 (C4 (Web Text))

Max Activating Token Index: 248

Text #16

Max Range: 1.0849. Min Range: -1.0849

Max Act: 0.8770. Min Act: -0.0001

Data Index: 713270 (C4 (Web Text))

Max Activating Token Index: 57

Text #17

Max Range: 1.0849. Min Range: -1.0849

Max Act: 0.7871. Min Act: -0.0001

Data Index: 1000902 (C4 (Web Text))

Max Activating Token Index: 379

Text #18

Max Range: 1.0849. Min Range: -1.0849

Max Act: 0.9013. Min Act: -0.0001

Data Index: 842163 (C4 (Web Text))

Max Activating Token Index: 782

Text #19

Max Range: 1.0849. Min Range: -1.0849

Max Act: 0.9222. Min Act: -0.0001

Data Index: 478986 (C4 (Web Text))

Max Activating Token Index: 444