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

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

Neuron 1839 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5065. Min Range: -0.5065

Max Act: 0.5065. Min Act: -0.0000

Data Index: 1165429 (C4 (Web Text))

Max Activating Token Index: 137

Text #1

Max Range: 0.5065. Min Range: -0.5065

Max Act: 0.3714. Min Act: -0.0000

Data Index: 1006913 (C4 (Web Text))

Max Activating Token Index: 193

Text #2

Max Range: 0.5065. Min Range: -0.5065

Max Act: 0.3295. Min Act: -0.0000

Data Index: 1620145 (Python Code)

Max Activating Token Index: 708

Text #3

Max Range: 0.5065. Min Range: -0.5065

Max Act: 0.3252. Min Act: -0.0000

Data Index: 683559 (C4 (Web Text))

Max Activating Token Index: 968

Text #4

Max Range: 0.5065. Min Range: -0.5065

Max Act: 0.3359. Min Act: -0.0000

Data Index: 1359554 (C4 (Web Text))

Max Activating Token Index: 256

Text #5

Max Range: 0.5065. Min Range: -0.5065

Max Act: 0.3217. Min Act: -0.0000

Data Index: 877063 (C4 (Web Text))

Max Activating Token Index: 771

Text #6

Max Range: 0.5065. Min Range: -0.5065

Max Act: 0.3373. Min Act: -0.0000

Data Index: 42325 (C4 (Web Text))

Max Activating Token Index: 287

Text #7

Max Range: 0.5065. Min Range: -0.5065

Max Act: 0.3258. Min Act: -0.0000

Data Index: 1170415 (C4 (Web Text))

Max Activating Token Index: 287

Text #8

Max Range: 0.5065. Min Range: -0.5065

Max Act: 0.3213. Min Act: -0.0000

Data Index: 1468874 (Python Code)

Max Activating Token Index: 424

Text #9

Max Range: 0.5065. Min Range: -0.5065

Max Act: 0.3196. Min Act: -0.0000

Data Index: 199094 (C4 (Web Text))

Max Activating Token Index: 714

Text #10

Max Range: 0.5065. Min Range: -0.5065

Max Act: 0.3071. Min Act: -0.0000

Data Index: 100302 (C4 (Web Text))

Max Activating Token Index: 455

Text #11

Max Range: 0.5065. Min Range: -0.5065

Max Act: 0.3181. Min Act: -0.0000

Data Index: 1309822 (C4 (Web Text))

Max Activating Token Index: 684

Text #12

Max Range: 0.5065. Min Range: -0.5065

Max Act: 0.2992. Min Act: -0.0000

Data Index: 1441333 (Python Code)

Max Activating Token Index: 957

Text #13

Max Range: 0.5065. Min Range: -0.5065

Max Act: 0.3559. Min Act: -0.0000

Data Index: 1498913 (Python Code)

Max Activating Token Index: 519

Text #14

Max Range: 0.5065. Min Range: -0.5065

Max Act: 0.3076. Min Act: -0.0000

Data Index: 804517 (C4 (Web Text))

Max Activating Token Index: 356

Text #15

Max Range: 0.5065. Min Range: -0.5065

Max Act: 0.3089. Min Act: -0.0000

Data Index: 1114128 (C4 (Web Text))

Max Activating Token Index: 404

Text #16

Max Range: 0.5065. Min Range: -0.5065

Max Act: 0.2932. Min Act: -0.0000

Data Index: 721367 (C4 (Web Text))

Max Activating Token Index: 435

Text #17

Max Range: 0.5065. Min Range: -0.5065

Max Act: 0.3043. Min Act: -0.0000

Data Index: 1320678 (C4 (Web Text))

Max Activating Token Index: 354

Text #18

Max Range: 0.5065. Min Range: -0.5065

Max Act: 0.3041. Min Act: -0.0000

Data Index: 858660 (C4 (Web Text))

Max Activating Token Index: 625

Text #19

Max Range: 0.5065. Min Range: -0.5065

Max Act: 0.2951. Min Act: -0.0000

Data Index: 366997 (C4 (Web Text))

Max Activating Token Index: 433