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

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

Neuron 642 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.9341. Min Range: -2.9341

Max Act: 2.9341. Min Act: -0.0000

Data Index: 1553771 (Python Code)

Max Activating Token Index: 491

Text #1

Max Range: 2.9341. Min Range: -2.9341

Max Act: 2.6416. Min Act: -0.0000

Data Index: 1592492 (Python Code)

Max Activating Token Index: 900

Text #2

Max Range: 2.9341. Min Range: -2.9341

Max Act: 2.5550. Min Act: -0.0000

Data Index: 1621576 (Python Code)

Max Activating Token Index: 883

Text #3

Max Range: 2.9341. Min Range: -2.9341

Max Act: 2.8529. Min Act: -0.0000

Data Index: 1555486 (Python Code)

Max Activating Token Index: 791

Text #4

Max Range: 2.9341. Min Range: -2.9341

Max Act: 2.3286. Min Act: -0.0000

Data Index: 1614239 (Python Code)

Max Activating Token Index: 192

Text #5

Max Range: 2.9341. Min Range: -2.9341

Max Act: 2.3176. Min Act: -0.0000

Data Index: 1532306 (Python Code)

Max Activating Token Index: 888

Text #6

Max Range: 2.9341. Min Range: -2.9341

Max Act: 2.4098. Min Act: -0.0000

Data Index: 1451338 (Python Code)

Max Activating Token Index: 404

Text #7

Max Range: 2.9341. Min Range: -2.9341

Max Act: 2.3938. Min Act: -0.0000

Data Index: 1519552 (Python Code)

Max Activating Token Index: 906

Text #8

Max Range: 2.9341. Min Range: -2.9341

Max Act: 2.4552. Min Act: -0.0000

Data Index: 1630535 (Python Code)

Max Activating Token Index: 394

Text #9

Max Range: 2.9341. Min Range: -2.9341

Max Act: 2.2719. Min Act: -0.0000

Data Index: 1403979 (Python Code)

Max Activating Token Index: 248

Text #10

Max Range: 2.9341. Min Range: -2.9341

Max Act: 2.2847. Min Act: -0.0000

Data Index: 1504254 (Python Code)

Max Activating Token Index: 428

Text #11

Max Range: 2.9341. Min Range: -2.9341

Max Act: 2.2884. Min Act: -0.0000

Data Index: 1365369 (Python Code)

Max Activating Token Index: 232

Text #12

Max Range: 2.9341. Min Range: -2.9341

Max Act: 2.2224. Min Act: -0.0000

Data Index: 1594368 (Python Code)

Max Activating Token Index: 52

Text #13

Max Range: 2.9341. Min Range: -2.9341

Max Act: 2.2099. Min Act: -0.0000

Data Index: 1519476 (Python Code)

Max Activating Token Index: 927

Text #14

Max Range: 2.9341. Min Range: -2.9341

Max Act: 2.2135. Min Act: -0.0000

Data Index: 1422366 (Python Code)

Max Activating Token Index: 421

Text #15

Max Range: 2.9341. Min Range: -2.9341

Max Act: 2.2144. Min Act: -0.0000

Data Index: 1614796 (Python Code)

Max Activating Token Index: 387

Text #16

Max Range: 2.9341. Min Range: -2.9341

Max Act: 2.1976. Min Act: -0.0000

Data Index: 1363538 (Python Code)

Max Activating Token Index: 823

Text #17

Max Range: 2.9341. Min Range: -2.9341

Max Act: 2.2052. Min Act: -0.0000

Data Index: 1361456 (Python Code)

Max Activating Token Index: 224

Text #18

Max Range: 2.9341. Min Range: -2.9341

Max Act: 2.1952. Min Act: -0.0000

Data Index: 1616868 (Python Code)

Max Activating Token Index: 534

Text #19

Max Range: 2.9341. Min Range: -2.9341

Max Act: 2.2025. Min Act: -0.0000

Data Index: 1500754 (Python Code)

Max Activating Token Index: 803