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

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

Neuron 3604 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.6193. Min Range: -4.6193

Max Act: 4.6193. Min Act: -0.0000

Data Index: 407743 (C4 (Web Text))

Max Activating Token Index: 94

Text #1

Max Range: 4.6193. Min Range: -4.6193

Max Act: 4.4020. Min Act: -0.0000

Data Index: 51677 (C4 (Web Text))

Max Activating Token Index: 154

Text #2

Max Range: 4.6193. Min Range: -4.6193

Max Act: 4.6166. Min Act: -0.0000

Data Index: 910603 (C4 (Web Text))

Max Activating Token Index: 813

Text #3

Max Range: 4.6193. Min Range: -4.6193

Max Act: 4.3892. Min Act: -0.0000

Data Index: 360366 (C4 (Web Text))

Max Activating Token Index: 716

Text #4

Max Range: 4.6193. Min Range: -4.6193

Max Act: 3.9398. Min Act: -0.0000

Data Index: 536570 (C4 (Web Text))

Max Activating Token Index: 616

Text #5

Max Range: 4.6193. Min Range: -4.6193

Max Act: 4.3126. Min Act: -0.0000

Data Index: 893967 (C4 (Web Text))

Max Activating Token Index: 13

Text #6

Max Range: 4.6193. Min Range: -4.6193

Max Act: 4.2724. Min Act: -0.0000

Data Index: 1192982 (C4 (Web Text))

Max Activating Token Index: 595

Text #7

Max Range: 4.6193. Min Range: -4.6193

Max Act: 4.2258. Min Act: -0.0000

Data Index: 424776 (C4 (Web Text))

Max Activating Token Index: 250

Text #8

Max Range: 4.6193. Min Range: -4.6193

Max Act: 4.2428. Min Act: -0.0000

Data Index: 1076695 (C4 (Web Text))

Max Activating Token Index: 490

Text #9

Max Range: 4.6193. Min Range: -4.6193

Max Act: 4.2172. Min Act: -0.0000

Data Index: 734040 (C4 (Web Text))

Max Activating Token Index: 963

Text #10

Max Range: 4.6193. Min Range: -4.6193

Max Act: 3.9669. Min Act: -0.0000

Data Index: 1155946 (C4 (Web Text))

Max Activating Token Index: 5

Text #11

Max Range: 4.6193. Min Range: -4.6193

Max Act: 4.1152. Min Act: -0.0000

Data Index: 78200 (C4 (Web Text))

Max Activating Token Index: 186

Text #12

Max Range: 4.6193. Min Range: -4.6193

Max Act: 3.9110. Min Act: -0.0000

Data Index: 749825 (C4 (Web Text))

Max Activating Token Index: 483

Text #13

Max Range: 4.6193. Min Range: -4.6193

Max Act: 4.1079. Min Act: -0.0000

Data Index: 861389 (C4 (Web Text))

Max Activating Token Index: 223

Text #14

Max Range: 4.6193. Min Range: -4.6193

Max Act: 4.0695. Min Act: -0.0000

Data Index: 1141093 (C4 (Web Text))

Max Activating Token Index: 380

Text #15

Max Range: 4.6193. Min Range: -4.6193

Max Act: 4.0649. Min Act: -0.0000

Data Index: 932244 (C4 (Web Text))

Max Activating Token Index: 559

Text #16

Max Range: 4.6193. Min Range: -4.6193

Max Act: 3.8922. Min Act: -0.0000

Data Index: 430674 (C4 (Web Text))

Max Activating Token Index: 795

Text #17

Max Range: 4.6193. Min Range: -4.6193

Max Act: 4.0415. Min Act: -0.0000

Data Index: 900021 (C4 (Web Text))

Max Activating Token Index: 147

Text #18

Max Range: 4.6193. Min Range: -4.6193

Max Act: 4.0451. Min Act: -0.0000

Data Index: 103947 (C4 (Web Text))

Max Activating Token Index: 83

Text #19

Max Range: 4.6193. Min Range: -4.6193

Max Act: 4.0375. Min Act: -0.0000

Data Index: 1167873 (C4 (Web Text))

Max Activating Token Index: 472