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

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

Neuron 847 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5126. Min Range: -0.5126

Max Act: 0.5126. Min Act: -0.0003

Data Index: 1329764 (C4 (Web Text))

Max Activating Token Index: 758

Text #1

Max Range: 0.5126. Min Range: -0.5126

Max Act: 0.4561. Min Act: -0.0002

Data Index: 1482914 (Python Code)

Max Activating Token Index: 157

Text #2

Max Range: 0.5126. Min Range: -0.5126

Max Act: 0.4776. Min Act: -0.0002

Data Index: 1599941 (Python Code)

Max Activating Token Index: 682

Text #3

Max Range: 0.5126. Min Range: -0.5126

Max Act: 0.4759. Min Act: -0.0002

Data Index: 269289 (C4 (Web Text))

Max Activating Token Index: 265

Text #4

Max Range: 0.5126. Min Range: -0.5126

Max Act: 0.4381. Min Act: -0.0002

Data Index: 1447363 (Python Code)

Max Activating Token Index: 561

Text #5

Max Range: 0.5126. Min Range: -0.5126

Max Act: 0.4265. Min Act: -0.0002

Data Index: 1469687 (Python Code)

Max Activating Token Index: 271

Text #6

Max Range: 0.5126. Min Range: -0.5126

Max Act: 0.4227. Min Act: -0.0002

Data Index: 1424542 (Python Code)

Max Activating Token Index: 420

Text #7

Max Range: 0.5126. Min Range: -0.5126

Max Act: 0.4221. Min Act: -0.0003

Data Index: 1430986 (Python Code)

Max Activating Token Index: 98

Text #8

Max Range: 0.5126. Min Range: -0.5126

Max Act: 0.4042. Min Act: -0.0003

Data Index: 1505624 (Python Code)

Max Activating Token Index: 297

Text #9

Max Range: 0.5126. Min Range: -0.5126

Max Act: 0.4164. Min Act: -0.0002

Data Index: 1544872 (Python Code)

Max Activating Token Index: 567

Text #10

Max Range: 0.5126. Min Range: -0.5126

Max Act: 0.4126. Min Act: -0.0002

Data Index: 1593334 (Python Code)

Max Activating Token Index: 588

Text #11

Max Range: 0.5126. Min Range: -0.5126

Max Act: 0.4408. Min Act: -0.0003

Data Index: 799269 (C4 (Web Text))

Max Activating Token Index: 289

Text #12

Max Range: 0.5126. Min Range: -0.5126

Max Act: 0.4093. Min Act: -0.0002

Data Index: 1568254 (Python Code)

Max Activating Token Index: 305

Text #13

Max Range: 0.5126. Min Range: -0.5126

Max Act: 0.4091. Min Act: -0.0002

Data Index: 422622 (C4 (Web Text))

Max Activating Token Index: 543

Text #14

Max Range: 0.5126. Min Range: -0.5126

Max Act: 0.4091. Min Act: -0.0002

Data Index: 1419084 (Python Code)

Max Activating Token Index: 277

Text #15

Max Range: 0.5126. Min Range: -0.5126

Max Act: 0.3934. Min Act: -0.0002

Data Index: 1482829 (Python Code)

Max Activating Token Index: 538

Text #16

Max Range: 0.5126. Min Range: -0.5126

Max Act: 0.4184. Min Act: -0.0002

Data Index: 1525472 (Python Code)

Max Activating Token Index: 88

Text #17

Max Range: 0.5126. Min Range: -0.5126

Max Act: 0.4054. Min Act: -0.0002

Data Index: 1421303 (Python Code)

Max Activating Token Index: 533

Text #18

Max Range: 0.5126. Min Range: -0.5126

Max Act: 0.4132. Min Act: -0.0003

Data Index: 1498658 (Python Code)

Max Activating Token Index: 330

Text #19

Max Range: 0.5126. Min Range: -0.5126

Max Act: 0.3972. Min Act: -0.0003

Data Index: 1569326 (Python Code)

Max Activating Token Index: 473