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

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

Neuron 3067 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0305. Min Range: -1.0305

Max Act: 1.0305. Min Act: -0.0001

Data Index: 918263 (C4 (Web Text))

Max Activating Token Index: 674

Text #1

Max Range: 1.0305. Min Range: -1.0305

Max Act: 0.8786. Min Act: -0.0001

Data Index: 1650584 (Python Code)

Max Activating Token Index: 259

Text #2

Max Range: 1.0305. Min Range: -1.0305

Max Act: 0.8663. Min Act: -0.0001

Data Index: 1270167 (C4 (Web Text))

Max Activating Token Index: 141

Text #3

Max Range: 1.0305. Min Range: -1.0305

Max Act: 0.7875. Min Act: -0.0001

Data Index: 1595430 (Python Code)

Max Activating Token Index: 100

Text #4

Max Range: 1.0305. Min Range: -1.0305

Max Act: 0.8325. Min Act: -0.0001

Data Index: 458584 (C4 (Web Text))

Max Activating Token Index: 445

Text #5

Max Range: 1.0305. Min Range: -1.0305

Max Act: 0.8239. Min Act: -0.0001

Data Index: 1385157 (Python Code)

Max Activating Token Index: 128

Text #6

Max Range: 1.0305. Min Range: -1.0305

Max Act: 0.7669. Min Act: -0.0001

Data Index: 1551838 (Python Code)

Max Activating Token Index: 331

Text #7

Max Range: 1.0305. Min Range: -1.0305

Max Act: 0.8106. Min Act: -0.0001

Data Index: 1386663 (Python Code)

Max Activating Token Index: 309

Text #8

Max Range: 1.0305. Min Range: -1.0305

Max Act: 0.8973. Min Act: -0.0001

Data Index: 1091546 (C4 (Web Text))

Max Activating Token Index: 915

Text #9

Max Range: 1.0305. Min Range: -1.0305

Max Act: 0.7208. Min Act: -0.0001

Data Index: 1605517 (Python Code)

Max Activating Token Index: 93

Text #10

Max Range: 1.0305. Min Range: -1.0305

Max Act: 0.7879. Min Act: -0.0001

Data Index: 1482984 (Python Code)

Max Activating Token Index: 46

Text #11

Max Range: 1.0305. Min Range: -1.0305

Max Act: 0.7233. Min Act: -0.0000

Data Index: 1486795 (Python Code)

Max Activating Token Index: 216

Text #12

Max Range: 1.0305. Min Range: -1.0305

Max Act: 0.7477. Min Act: -0.0001

Data Index: 1469923 (Python Code)

Max Activating Token Index: 478

Text #13

Max Range: 1.0305. Min Range: -1.0305

Max Act: 0.7436. Min Act: -0.0001

Data Index: 662301 (C4 (Web Text))

Max Activating Token Index: 81

Text #14

Max Range: 1.0305. Min Range: -1.0305

Max Act: 0.7173. Min Act: -0.0001

Data Index: 1366542 (Python Code)

Max Activating Token Index: 49

Text #15

Max Range: 1.0305. Min Range: -1.0305

Max Act: 0.8071. Min Act: -0.0001

Data Index: 874602 (C4 (Web Text))

Max Activating Token Index: 889

Text #16

Max Range: 1.0305. Min Range: -1.0305

Max Act: 0.7091. Min Act: -0.0001

Data Index: 1424472 (Python Code)

Max Activating Token Index: 408

Text #17

Max Range: 1.0305. Min Range: -1.0305

Max Act: 0.7048. Min Act: -0.0001

Data Index: 1532595 (Python Code)

Max Activating Token Index: 183

Text #18

Max Range: 1.0305. Min Range: -1.0305

Max Act: 0.7754. Min Act: -0.0001

Data Index: 660303 (C4 (Web Text))

Max Activating Token Index: 120

Text #19

Max Range: 1.0305. Min Range: -1.0305

Max Act: 0.7209. Min Act: -0.0001

Data Index: 1419109 (Python Code)

Max Activating Token Index: 109