Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 4731 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 4.7305. Min Range: -4.7305

Max Act: 4.7305. Min Act: -0.0000

Data Index: 808503 (C4 (Web Text))

Max Activating Token Index: 729

Text #1

Max Range: 4.7305. Min Range: -4.7305

Max Act: 3.5038. Min Act: -0.0000

Data Index: 145169 (C4 (Web Text))

Max Activating Token Index: 1007

Text #2

Max Range: 4.7305. Min Range: -4.7305

Max Act: 3.5306. Min Act: -0.0000

Data Index: 708895 (C4 (Web Text))

Max Activating Token Index: 266

Text #3

Max Range: 4.7305. Min Range: -4.7305

Max Act: 3.4075. Min Act: -0.0000

Data Index: 1017624 (C4 (Web Text))

Max Activating Token Index: 409

Text #4

Max Range: 4.7305. Min Range: -4.7305

Max Act: 3.3439. Min Act: -0.0000

Data Index: 396552 (C4 (Web Text))

Max Activating Token Index: 369

Text #5

Max Range: 4.7305. Min Range: -4.7305

Max Act: 3.4395. Min Act: -0.0000

Data Index: 843043 (C4 (Web Text))

Max Activating Token Index: 317

Text #6

Max Range: 4.7305. Min Range: -4.7305

Max Act: 3.1699. Min Act: -0.0000

Data Index: 599253 (C4 (Web Text))

Max Activating Token Index: 714

Text #7

Max Range: 4.7305. Min Range: -4.7305

Max Act: 3.1242. Min Act: -0.0000

Data Index: 703862 (C4 (Web Text))

Max Activating Token Index: 570

Text #8

Max Range: 4.7305. Min Range: -4.7305

Max Act: 3.2760. Min Act: -0.0000

Data Index: 418366 (C4 (Web Text))

Max Activating Token Index: 135

Text #9

Max Range: 4.7305. Min Range: -4.7305

Max Act: 3.1100. Min Act: -0.0000

Data Index: 1107810 (C4 (Web Text))

Max Activating Token Index: 667

Text #10

Max Range: 4.7305. Min Range: -4.7305

Max Act: 2.9655. Min Act: -0.0000

Data Index: 411370 (C4 (Web Text))

Max Activating Token Index: 72

Text #11

Max Range: 4.7305. Min Range: -4.7305

Max Act: 3.0720. Min Act: -0.0000

Data Index: 992214 (C4 (Web Text))

Max Activating Token Index: 265

Text #12

Max Range: 4.7305. Min Range: -4.7305

Max Act: 3.1309. Min Act: -0.0000

Data Index: 382007 (C4 (Web Text))

Max Activating Token Index: 378

Text #13

Max Range: 4.7305. Min Range: -4.7305

Max Act: 2.9526. Min Act: -0.0000

Data Index: 580499 (C4 (Web Text))

Max Activating Token Index: 776

Text #14

Max Range: 4.7305. Min Range: -4.7305

Max Act: 3.0669. Min Act: -0.0000

Data Index: 963824 (C4 (Web Text))

Max Activating Token Index: 441

Text #15

Max Range: 4.7305. Min Range: -4.7305

Max Act: 2.7604. Min Act: -0.0000

Data Index: 161089 (C4 (Web Text))

Max Activating Token Index: 789

Text #16

Max Range: 4.7305. Min Range: -4.7305

Max Act: 2.8700. Min Act: -0.0000

Data Index: 367438 (C4 (Web Text))

Max Activating Token Index: 828

Text #17

Max Range: 4.7305. Min Range: -4.7305

Max Act: 2.8559. Min Act: -0.0000

Data Index: 133698 (C4 (Web Text))

Max Activating Token Index: 448

Text #18

Max Range: 4.7305. Min Range: -4.7305

Max Act: 2.7906. Min Act: -0.0000

Data Index: 1048113 (C4 (Web Text))

Max Activating Token Index: 422

Text #19

Max Range: 4.7305. Min Range: -4.7305

Max Act: 2.7880. Min Act: -0.0000

Data Index: 193557 (C4 (Web Text))

Max Activating Token Index: 608