Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 1568 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.0327. Min Range: -0.0327

Max Act: 0.0327. Min Act: -0.0005

Data Index: 1538683 (Python Code)

Max Activating Token Index: 747

Text #1

Max Range: 0.0327. Min Range: -0.0327

Max Act: 0.0322. Min Act: -0.0005

Data Index: 687238 (C4 (Web Text))

Max Activating Token Index: 812

Text #2

Max Range: 0.0327. Min Range: -0.0327

Max Act: 0.0313. Min Act: -0.0005

Data Index: 731260 (C4 (Web Text))

Max Activating Token Index: 904

Text #3

Max Range: 0.0327. Min Range: -0.0327

Max Act: 0.0305. Min Act: -0.0005

Data Index: 486861 (C4 (Web Text))

Max Activating Token Index: 289

Text #4

Max Range: 0.0327. Min Range: -0.0327

Max Act: 0.0279. Min Act: -0.0005

Data Index: 389742 (C4 (Web Text))

Max Activating Token Index: 910

Text #5

Max Range: 0.0327. Min Range: -0.0327

Max Act: 0.0284. Min Act: -0.0005

Data Index: 757617 (C4 (Web Text))

Max Activating Token Index: 931

Text #6

Max Range: 0.0327. Min Range: -0.0327

Max Act: 0.0276. Min Act: -0.0005

Data Index: 579780 (C4 (Web Text))

Max Activating Token Index: 255

Text #7

Max Range: 0.0327. Min Range: -0.0327

Max Act: 0.0265. Min Act: -0.0005

Data Index: 1472050 (Python Code)

Max Activating Token Index: 908

Text #8

Max Range: 0.0327. Min Range: -0.0327

Max Act: 0.0262. Min Act: -0.0005

Data Index: 521283 (C4 (Web Text))

Max Activating Token Index: 929

Text #9

Max Range: 0.0327. Min Range: -0.0327

Max Act: 0.0268. Min Act: -0.0005

Data Index: 708735 (C4 (Web Text))

Max Activating Token Index: 276

Text #10

Max Range: 0.0327. Min Range: -0.0327

Max Act: 0.0270. Min Act: -0.0005

Data Index: 1058195 (C4 (Web Text))

Max Activating Token Index: 737

Text #11

Max Range: 0.0327. Min Range: -0.0327

Max Act: 0.0269. Min Act: -0.0005

Data Index: 79359 (C4 (Web Text))

Max Activating Token Index: 266

Text #12

Max Range: 0.0327. Min Range: -0.0327

Max Act: 0.0266. Min Act: -0.0005

Data Index: 760106 (C4 (Web Text))

Max Activating Token Index: 58

Text #13

Max Range: 0.0327. Min Range: -0.0327

Max Act: 0.0263. Min Act: -0.0005

Data Index: 1270388 (C4 (Web Text))

Max Activating Token Index: 878

Text #14

Max Range: 0.0327. Min Range: -0.0327

Max Act: 0.0258. Min Act: -0.0005

Data Index: 1324640 (C4 (Web Text))

Max Activating Token Index: 619

Text #15

Max Range: 0.0327. Min Range: -0.0327

Max Act: 0.0255. Min Act: -0.0005

Data Index: 717200 (C4 (Web Text))

Max Activating Token Index: 653

Text #16

Max Range: 0.0327. Min Range: -0.0327

Max Act: 0.0254. Min Act: -0.0005

Data Index: 1329797 (C4 (Web Text))

Max Activating Token Index: 73

Text #17

Max Range: 0.0327. Min Range: -0.0327

Max Act: 0.0252. Min Act: -0.0005

Data Index: 331798 (C4 (Web Text))

Max Activating Token Index: 784

Text #18

Max Range: 0.0327. Min Range: -0.0327

Max Act: 0.0250. Min Act: -0.0005

Data Index: 83359 (C4 (Web Text))

Max Activating Token Index: 563

Text #19

Max Range: 0.0327. Min Range: -0.0327

Max Act: 0.0244. Min Act: -0.0005

Data Index: 673087 (C4 (Web Text))

Max Activating Token Index: 342