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

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

Neuron 2085 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: 5.0259. Min Range: -5.0259

Max Act: 5.0259. Min Act: -0.0000

Data Index: 528728 (C4 (Web Text))

Max Activating Token Index: 426

Text #1

Max Range: 5.0259. Min Range: -5.0259

Max Act: 4.8067. Min Act: -0.0000

Data Index: 417892 (C4 (Web Text))

Max Activating Token Index: 163

Text #2

Max Range: 5.0259. Min Range: -5.0259

Max Act: 4.8548. Min Act: -0.0000

Data Index: 427573 (C4 (Web Text))

Max Activating Token Index: 472

Text #3

Max Range: 5.0259. Min Range: -5.0259

Max Act: 4.4435. Min Act: -0.0000

Data Index: 324491 (C4 (Web Text))

Max Activating Token Index: 474

Text #4

Max Range: 5.0259. Min Range: -5.0259

Max Act: 3.9565. Min Act: -0.0000

Data Index: 963318 (C4 (Web Text))

Max Activating Token Index: 131

Text #5

Max Range: 5.0259. Min Range: -5.0259

Max Act: 3.9278. Min Act: -0.0000

Data Index: 1036392 (C4 (Web Text))

Max Activating Token Index: 595

Text #6

Max Range: 5.0259. Min Range: -5.0259

Max Act: 4.0474. Min Act: -0.0000

Data Index: 645832 (C4 (Web Text))

Max Activating Token Index: 269

Text #7

Max Range: 5.0259. Min Range: -5.0259

Max Act: 4.0798. Min Act: -0.0000

Data Index: 282678 (C4 (Web Text))

Max Activating Token Index: 855

Text #8

Max Range: 5.0259. Min Range: -5.0259

Max Act: 3.5755. Min Act: -0.0000

Data Index: 1048047 (C4 (Web Text))

Max Activating Token Index: 186

Text #9

Max Range: 5.0259. Min Range: -5.0259

Max Act: 3.5484. Min Act: -0.0000

Data Index: 680742 (C4 (Web Text))

Max Activating Token Index: 87

Text #10

Max Range: 5.0259. Min Range: -5.0259

Max Act: 3.8023. Min Act: -0.0000

Data Index: 869489 (C4 (Web Text))

Max Activating Token Index: 93

Text #11

Max Range: 5.0259. Min Range: -5.0259

Max Act: 3.9212. Min Act: -0.0000

Data Index: 801219 (C4 (Web Text))

Max Activating Token Index: 85

Text #12

Max Range: 5.0259. Min Range: -5.0259

Max Act: 3.4977. Min Act: -0.0000

Data Index: 1093245 (C4 (Web Text))

Max Activating Token Index: 10

Text #13

Max Range: 5.0259. Min Range: -5.0259

Max Act: 2.8331. Min Act: -0.0000

Data Index: 853822 (C4 (Web Text))

Max Activating Token Index: 317

Text #14

Max Range: 5.0259. Min Range: -5.0259

Max Act: 3.3670. Min Act: -0.0000

Data Index: 1008873 (C4 (Web Text))

Max Activating Token Index: 541

Text #15

Max Range: 5.0259. Min Range: -5.0259

Max Act: 3.5974. Min Act: -0.0000

Data Index: 649221 (C4 (Web Text))

Max Activating Token Index: 245

Text #16

Max Range: 5.0259. Min Range: -5.0259

Max Act: 3.1865. Min Act: -0.0000

Data Index: 761142 (C4 (Web Text))

Max Activating Token Index: 251

Text #17

Max Range: 5.0259. Min Range: -5.0259

Max Act: 3.0674. Min Act: -0.0000

Data Index: 1315129 (C4 (Web Text))

Max Activating Token Index: 996

Text #18

Max Range: 5.0259. Min Range: -5.0259

Max Act: 3.5408. Min Act: -0.0000

Data Index: 1140915 (C4 (Web Text))

Max Activating Token Index: 37

Text #19

Max Range: 5.0259. Min Range: -5.0259

Max Act: 3.2315. Min Act: -0.0000

Data Index: 951792 (C4 (Web Text))

Max Activating Token Index: 67