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

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

Neuron 276 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0312. Min Range: -0.0312

Max Act: 0.0312. Min Act: -0.0005

Data Index: 812074 (C4 (Web Text))

Max Activating Token Index: 1015

Text #1

Max Range: 0.0312. Min Range: -0.0312

Max Act: 0.0270. Min Act: -0.0005

Data Index: 959593 (C4 (Web Text))

Max Activating Token Index: 754

Text #2

Max Range: 0.0312. Min Range: -0.0312

Max Act: 0.0265. Min Act: -0.0005

Data Index: 1411270 (Python Code)

Max Activating Token Index: 798

Text #3

Max Range: 0.0312. Min Range: -0.0312

Max Act: 0.0260. Min Act: -0.0005

Data Index: 1654471 (Python Code)

Max Activating Token Index: 333

Text #4

Max Range: 0.0312. Min Range: -0.0312

Max Act: 0.0238. Min Act: -0.0005

Data Index: 1628658 (Python Code)

Max Activating Token Index: 839

Text #5

Max Range: 0.0312. Min Range: -0.0312

Max Act: 0.0254. Min Act: -0.0005

Data Index: 495690 (C4 (Web Text))

Max Activating Token Index: 514

Text #6

Max Range: 0.0312. Min Range: -0.0312

Max Act: 0.0259. Min Act: -0.0005

Data Index: 1628325 (Python Code)

Max Activating Token Index: 515

Text #7

Max Range: 0.0312. Min Range: -0.0312

Max Act: 0.0261. Min Act: -0.0005

Data Index: 450283 (C4 (Web Text))

Max Activating Token Index: 965

Text #8

Max Range: 0.0312. Min Range: -0.0312

Max Act: 0.0264. Min Act: -0.0005

Data Index: 1446977 (Python Code)

Max Activating Token Index: 638

Text #9

Max Range: 0.0312. Min Range: -0.0312

Max Act: 0.0250. Min Act: -0.0005

Data Index: 221968 (C4 (Web Text))

Max Activating Token Index: 908

Text #10

Max Range: 0.0312. Min Range: -0.0312

Max Act: 0.0232. Min Act: -0.0005

Data Index: 1488737 (Python Code)

Max Activating Token Index: 650

Text #11

Max Range: 0.0312. Min Range: -0.0312

Max Act: 0.0249. Min Act: -0.0005

Data Index: 60857 (C4 (Web Text))

Max Activating Token Index: 52

Text #12

Max Range: 0.0312. Min Range: -0.0312

Max Act: 0.0258. Min Act: -0.0005

Data Index: 1470807 (Python Code)

Max Activating Token Index: 755

Text #13

Max Range: 0.0312. Min Range: -0.0312

Max Act: 0.0257. Min Act: -0.0005

Data Index: 1652684 (Python Code)

Max Activating Token Index: 304

Text #14

Max Range: 0.0312. Min Range: -0.0312

Max Act: 0.0250. Min Act: -0.0005

Data Index: 1601022 (Python Code)

Max Activating Token Index: 560

Text #15

Max Range: 0.0312. Min Range: -0.0312

Max Act: 0.0247. Min Act: -0.0005

Data Index: 1551632 (Python Code)

Max Activating Token Index: 543

Text #16

Max Range: 0.0312. Min Range: -0.0312

Max Act: 0.0237. Min Act: -0.0005

Data Index: 685954 (C4 (Web Text))

Max Activating Token Index: 583

Text #17

Max Range: 0.0312. Min Range: -0.0312

Max Act: 0.0230. Min Act: -0.0005

Data Index: 708730 (C4 (Web Text))

Max Activating Token Index: 540

Text #18

Max Range: 0.0312. Min Range: -0.0312

Max Act: 0.0234. Min Act: -0.0005

Data Index: 90675 (C4 (Web Text))

Max Activating Token Index: 424

Text #19

Max Range: 0.0312. Min Range: -0.0312

Max Act: 0.0238. Min Act: -0.0005

Data Index: 916627 (C4 (Web Text))

Max Activating Token Index: 258