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

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

Neuron 7 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: 2.3190. Min Range: -2.3190

Max Act: 2.3190. Min Act: -0.0000

Data Index: 954231 (C4 (Web Text))

Max Activating Token Index: 585

Text #1

Max Range: 2.3190. Min Range: -2.3190

Max Act: 2.0887. Min Act: -0.0000

Data Index: 553174 (C4 (Web Text))

Max Activating Token Index: 795

Text #2

Max Range: 2.3190. Min Range: -2.3190

Max Act: 2.0046. Min Act: -0.0000

Data Index: 590657 (C4 (Web Text))

Max Activating Token Index: 531

Text #3

Max Range: 2.3190. Min Range: -2.3190

Max Act: 1.9173. Min Act: -0.0000

Data Index: 670780 (C4 (Web Text))

Max Activating Token Index: 483

Text #4

Max Range: 2.3190. Min Range: -2.3190

Max Act: 1.8924. Min Act: -0.0000

Data Index: 1175227 (C4 (Web Text))

Max Activating Token Index: 707

Text #5

Max Range: 2.3190. Min Range: -2.3190

Max Act: 1.8924. Min Act: -0.0000

Data Index: 843688 (C4 (Web Text))

Max Activating Token Index: 369

Text #6

Max Range: 2.3190. Min Range: -2.3190

Max Act: 1.8766. Min Act: -0.0000

Data Index: 825777 (C4 (Web Text))

Max Activating Token Index: 340

Text #7

Max Range: 2.3190. Min Range: -2.3190

Max Act: 1.7750. Min Act: -0.0000

Data Index: 335768 (C4 (Web Text))

Max Activating Token Index: 416

Text #8

Max Range: 2.3190. Min Range: -2.3190

Max Act: 1.8516. Min Act: -0.0000

Data Index: 532483 (C4 (Web Text))

Max Activating Token Index: 941

Text #9

Max Range: 2.3190. Min Range: -2.3190

Max Act: 1.8168. Min Act: -0.0000

Data Index: 309919 (C4 (Web Text))

Max Activating Token Index: 855

Text #10

Max Range: 2.3190. Min Range: -2.3190

Max Act: 1.6331. Min Act: -0.0000

Data Index: 574811 (C4 (Web Text))

Max Activating Token Index: 380

Text #11

Max Range: 2.3190. Min Range: -2.3190

Max Act: 1.8202. Min Act: -0.0000

Data Index: 1118040 (C4 (Web Text))

Max Activating Token Index: 435

Text #12

Max Range: 2.3190. Min Range: -2.3190

Max Act: 1.7203. Min Act: -0.0000

Data Index: 405232 (C4 (Web Text))

Max Activating Token Index: 84

Text #13

Max Range: 2.3190. Min Range: -2.3190

Max Act: 1.8039. Min Act: -0.0000

Data Index: 200376 (C4 (Web Text))

Max Activating Token Index: 457

Text #14

Max Range: 2.3190. Min Range: -2.3190

Max Act: 1.5898. Min Act: -0.0000

Data Index: 259069 (C4 (Web Text))

Max Activating Token Index: 674

Text #15

Max Range: 2.3190. Min Range: -2.3190

Max Act: 1.6629. Min Act: -0.0000

Data Index: 877964 (C4 (Web Text))

Max Activating Token Index: 973

Text #16

Max Range: 2.3190. Min Range: -2.3190

Max Act: 1.6859. Min Act: -0.0000

Data Index: 79229 (C4 (Web Text))

Max Activating Token Index: 751

Text #17

Max Range: 2.3190. Min Range: -2.3190

Max Act: 1.6479. Min Act: -0.0000

Data Index: 487302 (C4 (Web Text))

Max Activating Token Index: 31

Text #18

Max Range: 2.3190. Min Range: -2.3190

Max Act: 1.7322. Min Act: -0.0000

Data Index: 1331613 (C4 (Web Text))

Max Activating Token Index: 934

Text #19

Max Range: 2.3190. Min Range: -2.3190

Max Act: 1.6080. Min Act: -0.0000

Data Index: 4852 (C4 (Web Text))

Max Activating Token Index: 591