Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 1503 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.8963. Min Range: -0.8963

Max Act: 0.8963. Min Act: 0.0000

Data Index: 1573616 (Python Code)

Max Activating Token Index: 500

Text #1

Max Range: 0.8963. Min Range: -0.8963

Max Act: 0.8726. Min Act: -0.0000

Data Index: 1480821 (Python Code)

Max Activating Token Index: 301

Text #2

Max Range: 0.8963. Min Range: -0.8963

Max Act: 0.8075. Min Act: -0.0000

Data Index: 1520781 (Python Code)

Max Activating Token Index: 205

Text #3

Max Range: 0.8963. Min Range: -0.8963

Max Act: 0.8223. Min Act: -0.0001

Data Index: 1378561 (Python Code)

Max Activating Token Index: 704

Text #4

Max Range: 0.8963. Min Range: -0.8963

Max Act: 0.8422. Min Act: -0.0000

Data Index: 1504106 (Python Code)

Max Activating Token Index: 575

Text #5

Max Range: 0.8963. Min Range: -0.8963

Max Act: 0.7618. Min Act: -0.0001

Data Index: 1372897 (Python Code)

Max Activating Token Index: 379

Text #6

Max Range: 0.8963. Min Range: -0.8963

Max Act: 0.7624. Min Act: -0.0001

Data Index: 1634692 (Python Code)

Max Activating Token Index: 228

Text #7

Max Range: 0.8963. Min Range: -0.8963

Max Act: 0.8041. Min Act: -0.0001

Data Index: 1435764 (Python Code)

Max Activating Token Index: 696

Text #8

Max Range: 0.8963. Min Range: -0.8963

Max Act: 0.7534. Min Act: -0.0000

Data Index: 1550563 (Python Code)

Max Activating Token Index: 896

Text #9

Max Range: 0.8963. Min Range: -0.8963

Max Act: 0.7750. Min Act: -0.0000

Data Index: 1598059 (Python Code)

Max Activating Token Index: 178

Text #10

Max Range: 0.8963. Min Range: -0.8963

Max Act: 0.6984. Min Act: -0.0000

Data Index: 1594192 (Python Code)

Max Activating Token Index: 204

Text #11

Max Range: 0.8963. Min Range: -0.8963

Max Act: 0.7106. Min Act: -0.0000

Data Index: 1479540 (Python Code)

Max Activating Token Index: 412

Text #12

Max Range: 0.8963. Min Range: -0.8963

Max Act: 0.6455. Min Act: 0.0001

Data Index: 1435125 (Python Code)

Max Activating Token Index: 658

Text #13

Max Range: 0.8963. Min Range: -0.8963

Max Act: 0.6644. Min Act: 0.0001

Data Index: 1460498 (Python Code)

Max Activating Token Index: 222

Text #14

Max Range: 0.8963. Min Range: -0.8963

Max Act: 0.6842. Min Act: -0.0000

Data Index: 1507331 (Python Code)

Max Activating Token Index: 194

Text #15

Max Range: 0.8963. Min Range: -0.8963

Max Act: 0.6250. Min Act: -0.0000

Data Index: 1600456 (Python Code)

Max Activating Token Index: 231

Text #16

Max Range: 0.8963. Min Range: -0.8963

Max Act: 0.6666. Min Act: -0.0000

Data Index: 1457243 (Python Code)

Max Activating Token Index: 304

Text #17

Max Range: 0.8963. Min Range: -0.8963

Max Act: 0.6629. Min Act: 0.0001

Data Index: 1511362 (Python Code)

Max Activating Token Index: 721

Text #18

Max Range: 0.8963. Min Range: -0.8963

Max Act: 0.6757. Min Act: -0.0000

Data Index: 1507835 (Python Code)

Max Activating Token Index: 246

Text #19

Max Range: 0.8963. Min Range: -0.8963

Max Act: 0.6458. Min Act: -0.0001

Data Index: 1393206 (Python Code)

Max Activating Token Index: 503