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

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

Neuron 4794 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.4065. Min Range: -1.4065

Max Act: 1.4065. Min Act: -0.0000

Data Index: 914432 (C4 (Web Text))

Max Activating Token Index: 156

Text #1

Max Range: 1.4065. Min Range: -1.4065

Max Act: 1.4008. Min Act: -0.0000

Data Index: 474251 (C4 (Web Text))

Max Activating Token Index: 228

Text #2

Max Range: 1.4065. Min Range: -1.4065

Max Act: 1.2424. Min Act: -0.0000

Data Index: 347450 (C4 (Web Text))

Max Activating Token Index: 358

Text #3

Max Range: 1.4065. Min Range: -1.4065

Max Act: 1.1884. Min Act: -0.0000

Data Index: 1333205 (C4 (Web Text))

Max Activating Token Index: 506

Text #4

Max Range: 1.4065. Min Range: -1.4065

Max Act: 1.1846. Min Act: -0.0000

Data Index: 291666 (C4 (Web Text))

Max Activating Token Index: 487

Text #5

Max Range: 1.4065. Min Range: -1.4065

Max Act: 1.2573. Min Act: -0.0000

Data Index: 316909 (C4 (Web Text))

Max Activating Token Index: 27

Text #6

Max Range: 1.4065. Min Range: -1.4065

Max Act: 1.2318. Min Act: -0.0000

Data Index: 815210 (C4 (Web Text))

Max Activating Token Index: 93

Text #7

Max Range: 1.4065. Min Range: -1.4065

Max Act: 1.1473. Min Act: -0.0000

Data Index: 1194260 (C4 (Web Text))

Max Activating Token Index: 1005

Text #8

Max Range: 1.4065. Min Range: -1.4065

Max Act: 1.1462. Min Act: -0.0000

Data Index: 682390 (C4 (Web Text))

Max Activating Token Index: 1014

Text #9

Max Range: 1.4065. Min Range: -1.4065

Max Act: 1.2064. Min Act: -0.0000

Data Index: 631457 (C4 (Web Text))

Max Activating Token Index: 535

Text #10

Max Range: 1.4065. Min Range: -1.4065

Max Act: 1.0487. Min Act: -0.0000

Data Index: 826731 (C4 (Web Text))

Max Activating Token Index: 225

Text #11

Max Range: 1.4065. Min Range: -1.4065

Max Act: 1.0671. Min Act: -0.0000

Data Index: 1262936 (C4 (Web Text))

Max Activating Token Index: 829

Text #12

Max Range: 1.4065. Min Range: -1.4065

Max Act: 1.0819. Min Act: -0.0000

Data Index: 577374 (C4 (Web Text))

Max Activating Token Index: 439

Text #13

Max Range: 1.4065. Min Range: -1.4065

Max Act: 1.0277. Min Act: -0.0000

Data Index: 628629 (C4 (Web Text))

Max Activating Token Index: 877

Text #14

Max Range: 1.4065. Min Range: -1.4065

Max Act: 0.9956. Min Act: -0.0000

Data Index: 1206822 (C4 (Web Text))

Max Activating Token Index: 819

Text #15

Max Range: 1.4065. Min Range: -1.4065

Max Act: 1.0958. Min Act: -0.0000

Data Index: 1355709 (C4 (Web Text))

Max Activating Token Index: 305

Text #16

Max Range: 1.4065. Min Range: -1.4065

Max Act: 0.9280. Min Act: -0.0000

Data Index: 681478 (C4 (Web Text))

Max Activating Token Index: 261

Text #17

Max Range: 1.4065. Min Range: -1.4065

Max Act: 0.9887. Min Act: -0.0000

Data Index: 576648 (C4 (Web Text))

Max Activating Token Index: 231

Text #18

Max Range: 1.4065. Min Range: -1.4065

Max Act: 0.9040. Min Act: -0.0000

Data Index: 555798 (C4 (Web Text))

Max Activating Token Index: 408

Text #19

Max Range: 1.4065. Min Range: -1.4065

Max Act: 0.9248. Min Act: -0.0000

Data Index: 1187629 (C4 (Web Text))

Max Activating Token Index: 520