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

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

Neuron 493 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: 4.0256. Min Range: -4.0256

Max Act: 4.0256. Min Act: -0.0000

Data Index: 235415 (C4 (Web Text))

Max Activating Token Index: 220

Text #1

Max Range: 4.0256. Min Range: -4.0256

Max Act: 3.9340. Min Act: -0.0000

Data Index: 881652 (C4 (Web Text))

Max Activating Token Index: 464

Text #2

Max Range: 4.0256. Min Range: -4.0256

Max Act: 3.4325. Min Act: -0.0000

Data Index: 455325 (C4 (Web Text))

Max Activating Token Index: 543

Text #3

Max Range: 4.0256. Min Range: -4.0256

Max Act: 3.1996. Min Act: -0.0000

Data Index: 1247885 (C4 (Web Text))

Max Activating Token Index: 584

Text #4

Max Range: 4.0256. Min Range: -4.0256

Max Act: 3.0733. Min Act: -0.0000

Data Index: 377706 (C4 (Web Text))

Max Activating Token Index: 212

Text #5

Max Range: 4.0256. Min Range: -4.0256

Max Act: 3.1718. Min Act: -0.0000

Data Index: 146605 (C4 (Web Text))

Max Activating Token Index: 710

Text #6

Max Range: 4.0256. Min Range: -4.0256

Max Act: 3.1353. Min Act: -0.0000

Data Index: 160904 (C4 (Web Text))

Max Activating Token Index: 454

Text #7

Max Range: 4.0256. Min Range: -4.0256

Max Act: 3.0569. Min Act: -0.0000

Data Index: 49365 (C4 (Web Text))

Max Activating Token Index: 659

Text #8

Max Range: 4.0256. Min Range: -4.0256

Max Act: 3.0298. Min Act: -0.0000

Data Index: 790472 (C4 (Web Text))

Max Activating Token Index: 275

Text #9

Max Range: 4.0256. Min Range: -4.0256

Max Act: 3.0012. Min Act: -0.0000

Data Index: 693063 (C4 (Web Text))

Max Activating Token Index: 299

Text #10

Max Range: 4.0256. Min Range: -4.0256

Max Act: 2.9753. Min Act: -0.0000

Data Index: 1096155 (C4 (Web Text))

Max Activating Token Index: 79

Text #11

Max Range: 4.0256. Min Range: -4.0256

Max Act: 2.9535. Min Act: -0.0000

Data Index: 1230068 (C4 (Web Text))

Max Activating Token Index: 335

Text #12

Max Range: 4.0256. Min Range: -4.0256

Max Act: 2.9574. Min Act: -0.0000

Data Index: 194052 (C4 (Web Text))

Max Activating Token Index: 241

Text #13

Max Range: 4.0256. Min Range: -4.0256

Max Act: 2.9308. Min Act: -0.0000

Data Index: 502821 (C4 (Web Text))

Max Activating Token Index: 284

Text #14

Max Range: 4.0256. Min Range: -4.0256

Max Act: 2.7288. Min Act: -0.0000

Data Index: 1248184 (C4 (Web Text))

Max Activating Token Index: 323

Text #15

Max Range: 4.0256. Min Range: -4.0256

Max Act: 2.8533. Min Act: -0.0000

Data Index: 731053 (C4 (Web Text))

Max Activating Token Index: 71

Text #16

Max Range: 4.0256. Min Range: -4.0256

Max Act: 2.8524. Min Act: -0.0000

Data Index: 632950 (C4 (Web Text))

Max Activating Token Index: 665

Text #17

Max Range: 4.0256. Min Range: -4.0256

Max Act: 2.9490. Min Act: -0.0000

Data Index: 70358 (C4 (Web Text))

Max Activating Token Index: 438

Text #18

Max Range: 4.0256. Min Range: -4.0256

Max Act: 2.8041. Min Act: -0.0000

Data Index: 917970 (C4 (Web Text))

Max Activating Token Index: 573

Text #19

Max Range: 4.0256. Min Range: -4.0256

Max Act: 2.6456. Min Act: -0.0000

Data Index: 388087 (C4 (Web Text))

Max Activating Token Index: 770