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

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

Neuron 3957 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.9756. Min Range: -3.9756

Max Act: 3.6837. Min Act: -0.0000

Data Index: 1407242 (Python Code)

Max Activating Token Index: 391

Text #1

Max Range: 3.9756. Min Range: -3.9756

Max Act: 3.9756. Min Act: -0.0000

Data Index: 1541396 (Python Code)

Max Activating Token Index: 930

Text #2

Max Range: 3.9756. Min Range: -3.9756

Max Act: 3.4202. Min Act: -0.0000

Data Index: 1440529 (Python Code)

Max Activating Token Index: 734

Text #3

Max Range: 3.9756. Min Range: -3.9756

Max Act: 3.5328. Min Act: -0.0000

Data Index: 1608694 (Python Code)

Max Activating Token Index: 297

Text #4

Max Range: 3.9756. Min Range: -3.9756

Max Act: 3.4508. Min Act: -0.0000

Data Index: 1366409 (Python Code)

Max Activating Token Index: 472

Text #5

Max Range: 3.9756. Min Range: -3.9756

Max Act: 3.2978. Min Act: -0.0000

Data Index: 1483163 (Python Code)

Max Activating Token Index: 965

Text #6

Max Range: 3.9756. Min Range: -3.9756

Max Act: 3.3169. Min Act: -0.0000

Data Index: 1405632 (Python Code)

Max Activating Token Index: 846

Text #7

Max Range: 3.9756. Min Range: -3.9756

Max Act: 3.3171. Min Act: -0.0000

Data Index: 1613468 (Python Code)

Max Activating Token Index: 383

Text #8

Max Range: 3.9756. Min Range: -3.9756

Max Act: 2.9433. Min Act: -0.0000

Data Index: 1437030 (Python Code)

Max Activating Token Index: 603

Text #9

Max Range: 3.9756. Min Range: -3.9756

Max Act: 3.1136. Min Act: -0.0000

Data Index: 1382732 (Python Code)

Max Activating Token Index: 208

Text #10

Max Range: 3.9756. Min Range: -3.9756

Max Act: 2.9311. Min Act: -0.0000

Data Index: 1399716 (Python Code)

Max Activating Token Index: 388

Text #11

Max Range: 3.9756. Min Range: -3.9756

Max Act: 2.8212. Min Act: -0.0000

Data Index: 1514202 (Python Code)

Max Activating Token Index: 554

Text #12

Max Range: 3.9756. Min Range: -3.9756

Max Act: 2.6805. Min Act: -0.0000

Data Index: 1391851 (Python Code)

Max Activating Token Index: 397

Text #13

Max Range: 3.9756. Min Range: -3.9756

Max Act: 2.7259. Min Act: -0.0000

Data Index: 1400726 (Python Code)

Max Activating Token Index: 746

Text #14

Max Range: 3.9756. Min Range: -3.9756

Max Act: 2.4519. Min Act: -0.0000

Data Index: 1519553 (Python Code)

Max Activating Token Index: 380

Text #15

Max Range: 3.9756. Min Range: -3.9756

Max Act: 2.7267. Min Act: -0.0000

Data Index: 1640351 (Python Code)

Max Activating Token Index: 958

Text #16

Max Range: 3.9756. Min Range: -3.9756

Max Act: 2.6641. Min Act: -0.0000

Data Index: 1519324 (Python Code)

Max Activating Token Index: 242

Text #17

Max Range: 3.9756. Min Range: -3.9756

Max Act: 2.5274. Min Act: -0.0000

Data Index: 1613637 (Python Code)

Max Activating Token Index: 261

Text #18

Max Range: 3.9756. Min Range: -3.9756

Max Act: 2.6610. Min Act: -0.0000

Data Index: 1415909 (Python Code)

Max Activating Token Index: 338

Text #19

Max Range: 3.9756. Min Range: -3.9756

Max Act: 2.6231. Min Act: -0.0000

Data Index: 1469946 (Python Code)

Max Activating Token Index: 771