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

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

Neuron 3537 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3033. Min Range: -0.3033

Max Act: 0.2992. Min Act: -0.0001

Data Index: 726762 (C4 (Web Text))

Max Activating Token Index: 182

Text #1

Max Range: 0.3033. Min Range: -0.3033

Max Act: 0.3020. Min Act: -0.0001

Data Index: 1211994 (C4 (Web Text))

Max Activating Token Index: 103

Text #2

Max Range: 0.3033. Min Range: -0.3033

Max Act: 0.3033. Min Act: -0.0001

Data Index: 554127 (C4 (Web Text))

Max Activating Token Index: 80

Text #3

Max Range: 0.3033. Min Range: -0.3033

Max Act: 0.2749. Min Act: -0.0001

Data Index: 547058 (C4 (Web Text))

Max Activating Token Index: 506

Text #4

Max Range: 0.3033. Min Range: -0.3033

Max Act: 0.2794. Min Act: -0.0001

Data Index: 594136 (C4 (Web Text))

Max Activating Token Index: 882

Text #5

Max Range: 0.3033. Min Range: -0.3033

Max Act: 0.2564. Min Act: -0.0001

Data Index: 990552 (C4 (Web Text))

Max Activating Token Index: 807

Text #6

Max Range: 0.3033. Min Range: -0.3033

Max Act: 0.2477. Min Act: -0.0001

Data Index: 821066 (C4 (Web Text))

Max Activating Token Index: 838

Text #7

Max Range: 0.3033. Min Range: -0.3033

Max Act: 0.2544. Min Act: -0.0001

Data Index: 445512 (C4 (Web Text))

Max Activating Token Index: 951

Text #8

Max Range: 0.3033. Min Range: -0.3033

Max Act: 0.2346. Min Act: -0.0001

Data Index: 933454 (C4 (Web Text))

Max Activating Token Index: 146

Text #9

Max Range: 0.3033. Min Range: -0.3033

Max Act: 0.2298. Min Act: -0.0001

Data Index: 466511 (C4 (Web Text))

Max Activating Token Index: 406

Text #10

Max Range: 0.3033. Min Range: -0.3033

Max Act: 0.2322. Min Act: -0.0001

Data Index: 211807 (C4 (Web Text))

Max Activating Token Index: 657

Text #11

Max Range: 0.3033. Min Range: -0.3033

Max Act: 0.2218. Min Act: -0.0001

Data Index: 736456 (C4 (Web Text))

Max Activating Token Index: 262

Text #12

Max Range: 0.3033. Min Range: -0.3033

Max Act: 0.2148. Min Act: -0.0001

Data Index: 157752 (C4 (Web Text))

Max Activating Token Index: 250

Text #13

Max Range: 0.3033. Min Range: -0.3033

Max Act: 0.2321. Min Act: -0.0001

Data Index: 234768 (C4 (Web Text))

Max Activating Token Index: 941

Text #14

Max Range: 0.3033. Min Range: -0.3033

Max Act: 0.2255. Min Act: -0.0001

Data Index: 314213 (C4 (Web Text))

Max Activating Token Index: 86

Text #15

Max Range: 0.3033. Min Range: -0.3033

Max Act: 0.2156. Min Act: -0.0001

Data Index: 1004192 (C4 (Web Text))

Max Activating Token Index: 561

Text #16

Max Range: 0.3033. Min Range: -0.3033

Max Act: 0.2156. Min Act: -0.0001

Data Index: 519855 (C4 (Web Text))

Max Activating Token Index: 284

Text #17

Max Range: 0.3033. Min Range: -0.3033

Max Act: 0.1991. Min Act: -0.0001

Data Index: 317704 (C4 (Web Text))

Max Activating Token Index: 315

Text #18

Max Range: 0.3033. Min Range: -0.3033

Max Act: 0.2263. Min Act: -0.0001

Data Index: 462485 (C4 (Web Text))

Max Activating Token Index: 499

Text #19

Max Range: 0.3033. Min Range: -0.3033

Max Act: 0.2260. Min Act: -0.0001

Data Index: 157443 (C4 (Web Text))

Max Activating Token Index: 219