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

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

Neuron 5249 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.7239. Min Range: -4.7239

Max Act: 4.7239. Min Act: -0.0000

Data Index: 1387063 (Python Code)

Max Activating Token Index: 21

Text #1

Max Range: 4.7239. Min Range: -4.7239

Max Act: 4.4004. Min Act: -0.0000

Data Index: 1493963 (Python Code)

Max Activating Token Index: 30

Text #2

Max Range: 4.7239. Min Range: -4.7239

Max Act: 4.2394. Min Act: -0.0000

Data Index: 1509303 (Python Code)

Max Activating Token Index: 4

Text #3

Max Range: 4.7239. Min Range: -4.7239

Max Act: 4.1177. Min Act: -0.0000

Data Index: 1576856 (Python Code)

Max Activating Token Index: 20

Text #4

Max Range: 4.7239. Min Range: -4.7239

Max Act: 4.0996. Min Act: -0.0000

Data Index: 1613803 (Python Code)

Max Activating Token Index: 13

Text #5

Max Range: 4.7239. Min Range: -4.7239

Max Act: 4.0680. Min Act: -0.0000

Data Index: 1523709 (Python Code)

Max Activating Token Index: 276

Text #6

Max Range: 4.7239. Min Range: -4.7239

Max Act: 4.0430. Min Act: -0.0000

Data Index: 1512493 (Python Code)

Max Activating Token Index: 7

Text #7

Max Range: 4.7239. Min Range: -4.7239

Max Act: 3.8275. Min Act: -0.0000

Data Index: 1510271 (Python Code)

Max Activating Token Index: 21

Text #8

Max Range: 4.7239. Min Range: -4.7239

Max Act: 3.9706. Min Act: -0.0000

Data Index: 1619348 (Python Code)

Max Activating Token Index: 532

Text #9

Max Range: 4.7239. Min Range: -4.7239

Max Act: 3.9400. Min Act: -0.0000

Data Index: 1500067 (Python Code)

Max Activating Token Index: 103

Text #10

Max Range: 4.7239. Min Range: -4.7239

Max Act: 4.0247. Min Act: -0.0000

Data Index: 1393365 (Python Code)

Max Activating Token Index: 25

Text #11

Max Range: 4.7239. Min Range: -4.7239

Max Act: 3.6751. Min Act: -0.0000

Data Index: 1505864 (Python Code)

Max Activating Token Index: 237

Text #12

Max Range: 4.7239. Min Range: -4.7239

Max Act: 3.9867. Min Act: -0.0000

Data Index: 1614632 (Python Code)

Max Activating Token Index: 364

Text #13

Max Range: 4.7239. Min Range: -4.7239

Max Act: 3.8034. Min Act: -0.0000

Data Index: 1504785 (Python Code)

Max Activating Token Index: 74

Text #14

Max Range: 4.7239. Min Range: -4.7239

Max Act: 3.7961. Min Act: -0.0000

Data Index: 1561276 (Python Code)

Max Activating Token Index: 23

Text #15

Max Range: 4.7239. Min Range: -4.7239

Max Act: 3.5626. Min Act: -0.0000

Data Index: 1516560 (Python Code)

Max Activating Token Index: 882

Text #16

Max Range: 4.7239. Min Range: -4.7239

Max Act: 3.7323. Min Act: -0.0000

Data Index: 1506143 (Python Code)

Max Activating Token Index: 37

Text #17

Max Range: 4.7239. Min Range: -4.7239

Max Act: 3.5174. Min Act: -0.0000

Data Index: 1550658 (Python Code)

Max Activating Token Index: 20

Text #18

Max Range: 4.7239. Min Range: -4.7239

Max Act: 3.6851. Min Act: -0.0000

Data Index: 1579400 (Python Code)

Max Activating Token Index: 629

Text #19

Max Range: 4.7239. Min Range: -4.7239

Max Act: 3.6757. Min Act: -0.0000

Data Index: 1393033 (Python Code)

Max Activating Token Index: 667