Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 4238 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.3213. Min Range: -0.3213

Max Act: 0.3180. Min Act: -0.0000

Data Index: 1634587 (Python Code)

Max Activating Token Index: 168

Text #1

Max Range: 0.3213. Min Range: -0.3213

Max Act: 0.3022. Min Act: -0.0000

Data Index: 1629580 (Python Code)

Max Activating Token Index: 522

Text #2

Max Range: 0.3213. Min Range: -0.3213

Max Act: 0.3213. Min Act: 0.0000

Data Index: 1465445 (Python Code)

Max Activating Token Index: 606

Text #3

Max Range: 0.3213. Min Range: -0.3213

Max Act: 0.2878. Min Act: -0.0000

Data Index: 1533351 (Python Code)

Max Activating Token Index: 741

Text #4

Max Range: 0.3213. Min Range: -0.3213

Max Act: 0.3040. Min Act: -0.0000

Data Index: 1423666 (Python Code)

Max Activating Token Index: 742

Text #5

Max Range: 0.3213. Min Range: -0.3213

Max Act: 0.3007. Min Act: -0.0000

Data Index: 1436380 (Python Code)

Max Activating Token Index: 129

Text #6

Max Range: 0.3213. Min Range: -0.3213

Max Act: 0.2856. Min Act: -0.0000

Data Index: 1654821 (Python Code)

Max Activating Token Index: 351

Text #7

Max Range: 0.3213. Min Range: -0.3213

Max Act: 0.2603. Min Act: -0.0000

Data Index: 1632882 (Python Code)

Max Activating Token Index: 1008

Text #8

Max Range: 0.3213. Min Range: -0.3213

Max Act: 0.2851. Min Act: -0.0000

Data Index: 1487229 (Python Code)

Max Activating Token Index: 787

Text #9

Max Range: 0.3213. Min Range: -0.3213

Max Act: 0.2738. Min Act: -0.0000

Data Index: 1535036 (Python Code)

Max Activating Token Index: 360

Text #10

Max Range: 0.3213. Min Range: -0.3213

Max Act: 0.2773. Min Act: -0.0000

Data Index: 1414749 (Python Code)

Max Activating Token Index: 624

Text #11

Max Range: 0.3213. Min Range: -0.3213

Max Act: 0.2564. Min Act: -0.0000

Data Index: 1448910 (Python Code)

Max Activating Token Index: 712

Text #12

Max Range: 0.3213. Min Range: -0.3213

Max Act: 0.2625. Min Act: -0.0000

Data Index: 1397932 (Python Code)

Max Activating Token Index: 692

Text #13

Max Range: 0.3213. Min Range: -0.3213

Max Act: 0.2593. Min Act: -0.0000

Data Index: 1465960 (Python Code)

Max Activating Token Index: 302

Text #14

Max Range: 0.3213. Min Range: -0.3213

Max Act: 0.2604. Min Act: -0.0000

Data Index: 1542069 (Python Code)

Max Activating Token Index: 328

Text #15

Max Range: 0.3213. Min Range: -0.3213

Max Act: 0.2562. Min Act: -0.0000

Data Index: 1532628 (Python Code)

Max Activating Token Index: 690

Text #16

Max Range: 0.3213. Min Range: -0.3213

Max Act: 0.2450. Min Act: -0.0000

Data Index: 1631017 (Python Code)

Max Activating Token Index: 231

Text #17

Max Range: 0.3213. Min Range: -0.3213

Max Act: 0.2421. Min Act: -0.0000

Data Index: 1409934 (Python Code)

Max Activating Token Index: 109

Text #18

Max Range: 0.3213. Min Range: -0.3213

Max Act: 0.2640. Min Act: -0.0000

Data Index: 1631415 (Python Code)

Max Activating Token Index: 743

Text #19

Max Range: 0.3213. Min Range: -0.3213

Max Act: 0.2179. Min Act: -0.0000

Data Index: 1452481 (Python Code)

Max Activating Token Index: 965