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

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

Neuron 921 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.3131. Min Range: -0.3131

Max Act: 0.3131. Min Act: -0.0001

Data Index: 1418449 (Python Code)

Max Activating Token Index: 20

Text #1

Max Range: 0.3131. Min Range: -0.3131

Max Act: 0.3086. Min Act: -0.0001

Data Index: 1564553 (Python Code)

Max Activating Token Index: 57

Text #2

Max Range: 0.3131. Min Range: -0.3131

Max Act: 0.2596. Min Act: -0.0001

Data Index: 1508030 (Python Code)

Max Activating Token Index: 5

Text #3

Max Range: 0.3131. Min Range: -0.3131

Max Act: 0.2464. Min Act: -0.0001

Data Index: 1520946 (Python Code)

Max Activating Token Index: 286

Text #4

Max Range: 0.3131. Min Range: -0.3131

Max Act: 0.2532. Min Act: -0.0001

Data Index: 1605302 (Python Code)

Max Activating Token Index: 161

Text #5

Max Range: 0.3131. Min Range: -0.3131

Max Act: 0.2489. Min Act: -0.0001

Data Index: 1598059 (Python Code)

Max Activating Token Index: 189

Text #6

Max Range: 0.3131. Min Range: -0.3131

Max Act: 0.2454. Min Act: -0.0001

Data Index: 1390504 (Python Code)

Max Activating Token Index: 89

Text #7

Max Range: 0.3131. Min Range: -0.3131

Max Act: 0.2384. Min Act: -0.0001

Data Index: 1458781 (Python Code)

Max Activating Token Index: 287

Text #8

Max Range: 0.3131. Min Range: -0.3131

Max Act: 0.2550. Min Act: -0.0001

Data Index: 1614943 (Python Code)

Max Activating Token Index: 48

Text #9

Max Range: 0.3131. Min Range: -0.3131

Max Act: 0.2361. Min Act: -0.0001

Data Index: 1555653 (Python Code)

Max Activating Token Index: 15

Text #10

Max Range: 0.3131. Min Range: -0.3131

Max Act: 0.2415. Min Act: -0.0001

Data Index: 1404309 (Python Code)

Max Activating Token Index: 27

Text #11

Max Range: 0.3131. Min Range: -0.3131

Max Act: 0.2410. Min Act: -0.0001

Data Index: 1579893 (Python Code)

Max Activating Token Index: 70

Text #12

Max Range: 0.3131. Min Range: -0.3131

Max Act: 0.2321. Min Act: -0.0001

Data Index: 1491340 (Python Code)

Max Activating Token Index: 42

Text #13

Max Range: 0.3131. Min Range: -0.3131

Max Act: 0.2164. Min Act: -0.0001

Data Index: 1550074 (Python Code)

Max Activating Token Index: 312

Text #14

Max Range: 0.3131. Min Range: -0.3131

Max Act: 0.2016. Min Act: -0.0001

Data Index: 1554712 (Python Code)

Max Activating Token Index: 373

Text #15

Max Range: 0.3131. Min Range: -0.3131

Max Act: 0.2456. Min Act: -0.0001

Data Index: 1588727 (Python Code)

Max Activating Token Index: 676

Text #16

Max Range: 0.3131. Min Range: -0.3131

Max Act: 0.2222. Min Act: -0.0001

Data Index: 1465955 (Python Code)

Max Activating Token Index: 103

Text #17

Max Range: 0.3131. Min Range: -0.3131

Max Act: 0.2279. Min Act: -0.0001

Data Index: 1493675 (Python Code)

Max Activating Token Index: 13

Text #18

Max Range: 0.3131. Min Range: -0.3131

Max Act: 0.1821. Min Act: -0.0001

Data Index: 1405975 (Python Code)

Max Activating Token Index: 373

Text #19

Max Range: 0.3131. Min Range: -0.3131

Max Act: 0.2398. Min Act: -0.0001

Data Index: 1466000 (Python Code)

Max Activating Token Index: 51