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

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

Neuron 1533 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: 0.2474. Min Range: -0.2474

Max Act: 0.2338. Min Act: -0.0000

Data Index: 1511580 (Python Code)

Max Activating Token Index: 100

Text #1

Max Range: 0.2474. Min Range: -0.2474

Max Act: 0.2314. Min Act: -0.0000

Data Index: 1390801 (Python Code)

Max Activating Token Index: 695

Text #2

Max Range: 0.2474. Min Range: -0.2474

Max Act: 0.2474. Min Act: -0.0000

Data Index: 64125 (C4 (Web Text))

Max Activating Token Index: 271

Text #3

Max Range: 0.2474. Min Range: -0.2474

Max Act: 0.2313. Min Act: -0.0000

Data Index: 1457870 (Python Code)

Max Activating Token Index: 539

Text #4

Max Range: 0.2474. Min Range: -0.2474

Max Act: 0.2391. Min Act: -0.0000

Data Index: 230145 (C4 (Web Text))

Max Activating Token Index: 294

Text #5

Max Range: 0.2474. Min Range: -0.2474

Max Act: 0.2001. Min Act: -0.0000

Data Index: 1103233 (C4 (Web Text))

Max Activating Token Index: 621

Text #6

Max Range: 0.2474. Min Range: -0.2474

Max Act: 0.2392. Min Act: -0.0000

Data Index: 707186 (C4 (Web Text))

Max Activating Token Index: 296

Text #7

Max Range: 0.2474. Min Range: -0.2474

Max Act: 0.2099. Min Act: -0.0000

Data Index: 1414883 (Python Code)

Max Activating Token Index: 779

Text #8

Max Range: 0.2474. Min Range: -0.2474

Max Act: 0.2001. Min Act: -0.0000

Data Index: 1440377 (Python Code)

Max Activating Token Index: 271

Text #9

Max Range: 0.2474. Min Range: -0.2474

Max Act: 0.2153. Min Act: -0.0000

Data Index: 662764 (C4 (Web Text))

Max Activating Token Index: 118

Text #10

Max Range: 0.2474. Min Range: -0.2474

Max Act: 0.2367. Min Act: -0.0000

Data Index: 525911 (C4 (Web Text))

Max Activating Token Index: 826

Text #11

Max Range: 0.2474. Min Range: -0.2474

Max Act: 0.1729. Min Act: -0.0000

Data Index: 1329201 (C4 (Web Text))

Max Activating Token Index: 402

Text #12

Max Range: 0.2474. Min Range: -0.2474

Max Act: 0.2045. Min Act: -0.0000

Data Index: 697791 (C4 (Web Text))

Max Activating Token Index: 389

Text #13

Max Range: 0.2474. Min Range: -0.2474

Max Act: 0.1951. Min Act: -0.0000

Data Index: 481293 (C4 (Web Text))

Max Activating Token Index: 294

Text #14

Max Range: 0.2474. Min Range: -0.2474

Max Act: 0.1788. Min Act: -0.0000

Data Index: 1263660 (C4 (Web Text))

Max Activating Token Index: 341

Text #15

Max Range: 0.2474. Min Range: -0.2474

Max Act: 0.1961. Min Act: -0.0000

Data Index: 885405 (C4 (Web Text))

Max Activating Token Index: 365

Text #16

Max Range: 0.2474. Min Range: -0.2474

Max Act: 0.2079. Min Act: -0.0000

Data Index: 1593031 (Python Code)

Max Activating Token Index: 995

Text #17

Max Range: 0.2474. Min Range: -0.2474

Max Act: 0.1845. Min Act: -0.0000

Data Index: 714583 (C4 (Web Text))

Max Activating Token Index: 164

Text #18

Max Range: 0.2474. Min Range: -0.2474

Max Act: 0.1839. Min Act: -0.0000

Data Index: 873351 (C4 (Web Text))

Max Activating Token Index: 175

Text #19

Max Range: 0.2474. Min Range: -0.2474

Max Act: 0.1910. Min Act: -0.0000

Data Index: 879939 (C4 (Web Text))

Max Activating Token Index: 535