Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 1107 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.9309. Min Range: -0.9309

Max Act: 0.9309. Min Act: -0.0003

Data Index: 1570739 (Python Code)

Max Activating Token Index: 117

Text #1

Max Range: 0.9309. Min Range: -0.9309

Max Act: 0.8237. Min Act: -0.0003

Data Index: 1438123 (Python Code)

Max Activating Token Index: 25

Text #2

Max Range: 0.9309. Min Range: -0.9309

Max Act: 0.7965. Min Act: -0.0003

Data Index: 1425761 (Python Code)

Max Activating Token Index: 31

Text #3

Max Range: 0.9309. Min Range: -0.9309

Max Act: 0.7203. Min Act: -0.0003

Data Index: 1389117 (Python Code)

Max Activating Token Index: 396

Text #4

Max Range: 0.9309. Min Range: -0.9309

Max Act: 0.7539. Min Act: -0.0003

Data Index: 1362897 (Python Code)

Max Activating Token Index: 14

Text #5

Max Range: 0.9309. Min Range: -0.9309

Max Act: 0.7728. Min Act: -0.0003

Data Index: 1574856 (Python Code)

Max Activating Token Index: 10

Text #6

Max Range: 0.9309. Min Range: -0.9309

Max Act: 0.7049. Min Act: -0.0004

Data Index: 1613137 (Python Code)

Max Activating Token Index: 200

Text #7

Max Range: 0.9309. Min Range: -0.9309

Max Act: 0.7582. Min Act: -0.0003

Data Index: 1448171 (Python Code)

Max Activating Token Index: 215

Text #8

Max Range: 0.9309. Min Range: -0.9309

Max Act: 0.7332. Min Act: -0.0003

Data Index: 1382361 (Python Code)

Max Activating Token Index: 32

Text #9

Max Range: 0.9309. Min Range: -0.9309

Max Act: 0.5699. Min Act: -0.0004

Data Index: 1432556 (Python Code)

Max Activating Token Index: 543

Text #10

Max Range: 0.9309. Min Range: -0.9309

Max Act: 0.7322. Min Act: -0.0003

Data Index: 1411342 (Python Code)

Max Activating Token Index: 38

Text #11

Max Range: 0.9309. Min Range: -0.9309

Max Act: 0.6874. Min Act: -0.0003

Data Index: 1583272 (Python Code)

Max Activating Token Index: 909

Text #12

Max Range: 0.9309. Min Range: -0.9309

Max Act: 0.7295. Min Act: -0.0003

Data Index: 1506178 (Python Code)

Max Activating Token Index: 375

Text #13

Max Range: 0.9309. Min Range: -0.9309

Max Act: 0.7323. Min Act: -0.0003

Data Index: 1377363 (Python Code)

Max Activating Token Index: 21

Text #14

Max Range: 0.9309. Min Range: -0.9309

Max Act: 0.7802. Min Act: -0.0003

Data Index: 1625842 (Python Code)

Max Activating Token Index: 55

Text #15

Max Range: 0.9309. Min Range: -0.9309

Max Act: 0.7298. Min Act: -0.0003

Data Index: 1393511 (Python Code)

Max Activating Token Index: 358

Text #16

Max Range: 0.9309. Min Range: -0.9309

Max Act: 0.7810. Min Act: -0.0003

Data Index: 1416858 (Python Code)

Max Activating Token Index: 591

Text #17

Max Range: 0.9309. Min Range: -0.9309

Max Act: 0.7628. Min Act: -0.0003

Data Index: 1627807 (Python Code)

Max Activating Token Index: 537

Text #18

Max Range: 0.9309. Min Range: -0.9309

Max Act: 0.7035. Min Act: -0.0004

Data Index: 1522104 (Python Code)

Max Activating Token Index: 290

Text #19

Max Range: 0.9309. Min Range: -0.9309

Max Act: 0.6579. Min Act: -0.0003

Data Index: 1595390 (Python Code)

Max Activating Token Index: 416