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

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

Neuron 2182 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: 0.3319. Min Range: -0.3319

Max Act: 0.3319. Min Act: -0.0000

Data Index: 1573678 (Python Code)

Max Activating Token Index: 346

Text #1

Max Range: 0.3319. Min Range: -0.3319

Max Act: 0.3240. Min Act: -0.0000

Data Index: 1527540 (Python Code)

Max Activating Token Index: 821

Text #2

Max Range: 0.3319. Min Range: -0.3319

Max Act: 0.3238. Min Act: -0.0000

Data Index: 1543166 (Python Code)

Max Activating Token Index: 888

Text #3

Max Range: 0.3319. Min Range: -0.3319

Max Act: 0.3103. Min Act: -0.0000

Data Index: 594968 (C4 (Web Text))

Max Activating Token Index: 252

Text #4

Max Range: 0.3319. Min Range: -0.3319

Max Act: 0.3028. Min Act: -0.0000

Data Index: 1385967 (Python Code)

Max Activating Token Index: 886

Text #5

Max Range: 0.3319. Min Range: -0.3319

Max Act: 0.2994. Min Act: -0.0000

Data Index: 1500683 (Python Code)

Max Activating Token Index: 883

Text #6

Max Range: 0.3319. Min Range: -0.3319

Max Act: 0.3015. Min Act: -0.0000

Data Index: 1551597 (Python Code)

Max Activating Token Index: 137

Text #7

Max Range: 0.3319. Min Range: -0.3319

Max Act: 0.2803. Min Act: -0.0000

Data Index: 1470611 (Python Code)

Max Activating Token Index: 502

Text #8

Max Range: 0.3319. Min Range: -0.3319

Max Act: 0.2604. Min Act: -0.0000

Data Index: 1516445 (Python Code)

Max Activating Token Index: 564

Text #9

Max Range: 0.3319. Min Range: -0.3319

Max Act: 0.2591. Min Act: -0.0000

Data Index: 1439154 (Python Code)

Max Activating Token Index: 1004

Text #10

Max Range: 0.3319. Min Range: -0.3319

Max Act: 0.2590. Min Act: -0.0000

Data Index: 1455720 (Python Code)

Max Activating Token Index: 746

Text #11

Max Range: 0.3319. Min Range: -0.3319

Max Act: 0.2763. Min Act: -0.0001

Data Index: 1437121 (Python Code)

Max Activating Token Index: 204

Text #12

Max Range: 0.3319. Min Range: -0.3319

Max Act: 0.2630. Min Act: -0.0000

Data Index: 1511911 (Python Code)

Max Activating Token Index: 670

Text #13

Max Range: 0.3319. Min Range: -0.3319

Max Act: 0.2716. Min Act: -0.0000

Data Index: 1297271 (C4 (Web Text))

Max Activating Token Index: 302

Text #14

Max Range: 0.3319. Min Range: -0.3319

Max Act: 0.2791. Min Act: -0.0000

Data Index: 1631800 (Python Code)

Max Activating Token Index: 167

Text #15

Max Range: 0.3319. Min Range: -0.3319

Max Act: 0.2493. Min Act: -0.0000

Data Index: 1534133 (Python Code)

Max Activating Token Index: 948

Text #16

Max Range: 0.3319. Min Range: -0.3319

Max Act: 0.2593. Min Act: -0.0000

Data Index: 1585164 (Python Code)

Max Activating Token Index: 273

Text #17

Max Range: 0.3319. Min Range: -0.3319

Max Act: 0.2672. Min Act: -0.0000

Data Index: 1420231 (Python Code)

Max Activating Token Index: 786

Text #18

Max Range: 0.3319. Min Range: -0.3319

Max Act: 0.2317. Min Act: -0.0000

Data Index: 1456194 (Python Code)

Max Activating Token Index: 628

Text #19

Max Range: 0.3319. Min Range: -0.3319

Max Act: 0.2549. Min Act: -0.0000

Data Index: 1514949 (Python Code)

Max Activating Token Index: 807