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

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

Neuron 1983 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7243. Min Range: -0.7243

Max Act: 0.7243. Min Act: -0.0000

Data Index: 1421439 (Python Code)

Max Activating Token Index: 255

Text #1

Max Range: 0.7243. Min Range: -0.7243

Max Act: 0.7202. Min Act: -0.0000

Data Index: 1364291 (Python Code)

Max Activating Token Index: 209

Text #2

Max Range: 0.7243. Min Range: -0.7243

Max Act: 0.7060. Min Act: -0.0000

Data Index: 1616186 (Python Code)

Max Activating Token Index: 639

Text #3

Max Range: 0.7243. Min Range: -0.7243

Max Act: 0.5929. Min Act: -0.0000

Data Index: 1554142 (Python Code)

Max Activating Token Index: 186

Text #4

Max Range: 0.7243. Min Range: -0.7243

Max Act: 0.6533. Min Act: -0.0000

Data Index: 1625168 (Python Code)

Max Activating Token Index: 29

Text #5

Max Range: 0.7243. Min Range: -0.7243

Max Act: 0.6668. Min Act: -0.0000

Data Index: 539407 (C4 (Web Text))

Max Activating Token Index: 744

Text #6

Max Range: 0.7243. Min Range: -0.7243

Max Act: 0.6267. Min Act: -0.0000

Data Index: 1514450 (Python Code)

Max Activating Token Index: 627

Text #7

Max Range: 0.7243. Min Range: -0.7243

Max Act: 0.6060. Min Act: -0.0000

Data Index: 680691 (C4 (Web Text))

Max Activating Token Index: 117

Text #8

Max Range: 0.7243. Min Range: -0.7243

Max Act: 0.5946. Min Act: -0.0000

Data Index: 1532457 (Python Code)

Max Activating Token Index: 207

Text #9

Max Range: 0.7243. Min Range: -0.7243

Max Act: 0.5581. Min Act: -0.0000

Data Index: 1409073 (Python Code)

Max Activating Token Index: 789

Text #10

Max Range: 0.7243. Min Range: -0.7243

Max Act: 0.5732. Min Act: -0.0000

Data Index: 1652035 (Python Code)

Max Activating Token Index: 262

Text #11

Max Range: 0.7243. Min Range: -0.7243

Max Act: 0.5821. Min Act: -0.0000

Data Index: 1413339 (Python Code)

Max Activating Token Index: 369

Text #12

Max Range: 0.7243. Min Range: -0.7243

Max Act: 0.5575. Min Act: -0.0000

Data Index: 878165 (C4 (Web Text))

Max Activating Token Index: 406

Text #13

Max Range: 0.7243. Min Range: -0.7243

Max Act: 0.5584. Min Act: -0.0000

Data Index: 1550812 (Python Code)

Max Activating Token Index: 930

Text #14

Max Range: 0.7243. Min Range: -0.7243

Max Act: 0.5933. Min Act: -0.0000

Data Index: 1565696 (Python Code)

Max Activating Token Index: 474

Text #15

Max Range: 0.7243. Min Range: -0.7243

Max Act: 0.5559. Min Act: -0.0000

Data Index: 476151 (C4 (Web Text))

Max Activating Token Index: 767

Text #16

Max Range: 0.7243. Min Range: -0.7243

Max Act: 0.5689. Min Act: -0.0000

Data Index: 14312 (C4 (Web Text))

Max Activating Token Index: 448

Text #17

Max Range: 0.7243. Min Range: -0.7243

Max Act: 0.6344. Min Act: -0.0000

Data Index: 1498138 (Python Code)

Max Activating Token Index: 784

Text #18

Max Range: 0.7243. Min Range: -0.7243

Max Act: 0.5328. Min Act: -0.0000

Data Index: 1562028 (Python Code)

Max Activating Token Index: 12

Text #19

Max Range: 0.7243. Min Range: -0.7243

Max Act: 0.5485. Min Act: -0.0000

Data Index: 1646960 (Python Code)

Max Activating Token Index: 130