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

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

Neuron 2192 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.4907. Min Range: -2.4907

Max Act: 2.4907. Min Act: -0.0000

Data Index: 1100425 (C4 (Web Text))

Max Activating Token Index: 455

Text #1

Max Range: 2.4907. Min Range: -2.4907

Max Act: 2.4502. Min Act: -0.0000

Data Index: 106148 (C4 (Web Text))

Max Activating Token Index: 60

Text #2

Max Range: 2.4907. Min Range: -2.4907

Max Act: 2.4377. Min Act: -0.0000

Data Index: 785887 (C4 (Web Text))

Max Activating Token Index: 676

Text #3

Max Range: 2.4907. Min Range: -2.4907

Max Act: 2.2333. Min Act: -0.0000

Data Index: 885284 (C4 (Web Text))

Max Activating Token Index: 33

Text #4

Max Range: 2.4907. Min Range: -2.4907

Max Act: 2.2585. Min Act: -0.0000

Data Index: 1305917 (C4 (Web Text))

Max Activating Token Index: 189

Text #5

Max Range: 2.4907. Min Range: -2.4907

Max Act: 2.1767. Min Act: -0.0000

Data Index: 575492 (C4 (Web Text))

Max Activating Token Index: 207

Text #6

Max Range: 2.4907. Min Range: -2.4907

Max Act: 2.1156. Min Act: -0.0000

Data Index: 155594 (C4 (Web Text))

Max Activating Token Index: 714

Text #7

Max Range: 2.4907. Min Range: -2.4907

Max Act: 2.0172. Min Act: -0.0000

Data Index: 186464 (C4 (Web Text))

Max Activating Token Index: 997

Text #8

Max Range: 2.4907. Min Range: -2.4907

Max Act: 2.1186. Min Act: -0.0000

Data Index: 510181 (C4 (Web Text))

Max Activating Token Index: 56

Text #9

Max Range: 2.4907. Min Range: -2.4907

Max Act: 2.0367. Min Act: -0.0000

Data Index: 1048313 (C4 (Web Text))

Max Activating Token Index: 430

Text #10

Max Range: 2.4907. Min Range: -2.4907

Max Act: 1.8204. Min Act: -0.0000

Data Index: 203379 (C4 (Web Text))

Max Activating Token Index: 839

Text #11

Max Range: 2.4907. Min Range: -2.4907

Max Act: 1.9977. Min Act: -0.0000

Data Index: 578473 (C4 (Web Text))

Max Activating Token Index: 219

Text #12

Max Range: 2.4907. Min Range: -2.4907

Max Act: 1.8744. Min Act: -0.0000

Data Index: 123718 (C4 (Web Text))

Max Activating Token Index: 32

Text #13

Max Range: 2.4907. Min Range: -2.4907

Max Act: 1.8488. Min Act: -0.0000

Data Index: 1197118 (C4 (Web Text))

Max Activating Token Index: 509

Text #14

Max Range: 2.4907. Min Range: -2.4907

Max Act: 1.8481. Min Act: -0.0000

Data Index: 362932 (C4 (Web Text))

Max Activating Token Index: 687

Text #15

Max Range: 2.4907. Min Range: -2.4907

Max Act: 1.8356. Min Act: -0.0000

Data Index: 878582 (C4 (Web Text))

Max Activating Token Index: 325

Text #16

Max Range: 2.4907. Min Range: -2.4907

Max Act: 1.9310. Min Act: -0.0000

Data Index: 286401 (C4 (Web Text))

Max Activating Token Index: 305

Text #17

Max Range: 2.4907. Min Range: -2.4907

Max Act: 1.9202. Min Act: -0.0000

Data Index: 902109 (C4 (Web Text))

Max Activating Token Index: 765

Text #18

Max Range: 2.4907. Min Range: -2.4907

Max Act: 1.9028. Min Act: -0.0000

Data Index: 1288063 (C4 (Web Text))

Max Activating Token Index: 49

Text #19

Max Range: 2.4907. Min Range: -2.4907

Max Act: 1.6934. Min Act: -0.0000

Data Index: 59294 (C4 (Web Text))

Max Activating Token Index: 1017