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

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

Neuron 2163 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.1176. Min Range: -2.1176

Max Act: 2.1176. Min Act: -0.0000

Data Index: 1054863 (C4 (Web Text))

Max Activating Token Index: 534

Text #1

Max Range: 2.1176. Min Range: -2.1176

Max Act: 1.9022. Min Act: -0.0000

Data Index: 961823 (C4 (Web Text))

Max Activating Token Index: 356

Text #2

Max Range: 2.1176. Min Range: -2.1176

Max Act: 2.0557. Min Act: -0.0000

Data Index: 1332714 (C4 (Web Text))

Max Activating Token Index: 295

Text #3

Max Range: 2.1176. Min Range: -2.1176

Max Act: 1.9956. Min Act: -0.0000

Data Index: 897265 (C4 (Web Text))

Max Activating Token Index: 834

Text #4

Max Range: 2.1176. Min Range: -2.1176

Max Act: 2.1011. Min Act: -0.0000

Data Index: 1399632 (Python Code)

Max Activating Token Index: 1005

Text #5

Max Range: 2.1176. Min Range: -2.1176

Max Act: 1.8702. Min Act: -0.0000

Data Index: 113380 (C4 (Web Text))

Max Activating Token Index: 481

Text #6

Max Range: 2.1176. Min Range: -2.1176

Max Act: 1.9393. Min Act: -0.0000

Data Index: 1316129 (C4 (Web Text))

Max Activating Token Index: 152

Text #7

Max Range: 2.1176. Min Range: -2.1176

Max Act: 1.8324. Min Act: -0.0000

Data Index: 1599680 (Python Code)

Max Activating Token Index: 712

Text #8

Max Range: 2.1176. Min Range: -2.1176

Max Act: 1.8957. Min Act: -0.0000

Data Index: 1600716 (Python Code)

Max Activating Token Index: 996

Text #9

Max Range: 2.1176. Min Range: -2.1176

Max Act: 1.6743. Min Act: -0.0000

Data Index: 1271995 (C4 (Web Text))

Max Activating Token Index: 595

Text #10

Max Range: 2.1176. Min Range: -2.1176

Max Act: 2.0001. Min Act: -0.0000

Data Index: 602277 (C4 (Web Text))

Max Activating Token Index: 975

Text #11

Max Range: 2.1176. Min Range: -2.1176

Max Act: 1.7646. Min Act: -0.0000

Data Index: 98923 (C4 (Web Text))

Max Activating Token Index: 447

Text #12

Max Range: 2.1176. Min Range: -2.1176

Max Act: 1.7722. Min Act: -0.0000

Data Index: 977422 (C4 (Web Text))

Max Activating Token Index: 733

Text #13

Max Range: 2.1176. Min Range: -2.1176

Max Act: 1.8517. Min Act: -0.0000

Data Index: 236105 (C4 (Web Text))

Max Activating Token Index: 79

Text #14

Max Range: 2.1176. Min Range: -2.1176

Max Act: 1.6590. Min Act: -0.0000

Data Index: 955051 (C4 (Web Text))

Max Activating Token Index: 953

Text #15

Max Range: 2.1176. Min Range: -2.1176

Max Act: 1.8439. Min Act: -0.0000

Data Index: 891914 (C4 (Web Text))

Max Activating Token Index: 60

Text #16

Max Range: 2.1176. Min Range: -2.1176

Max Act: 1.8231. Min Act: -0.0000

Data Index: 987496 (C4 (Web Text))

Max Activating Token Index: 326

Text #17

Max Range: 2.1176. Min Range: -2.1176

Max Act: 1.8456. Min Act: -0.0000

Data Index: 142806 (C4 (Web Text))

Max Activating Token Index: 157

Text #18

Max Range: 2.1176. Min Range: -2.1176

Max Act: 1.8075. Min Act: -0.0000

Data Index: 1603678 (Python Code)

Max Activating Token Index: 489

Text #19

Max Range: 2.1176. Min Range: -2.1176

Max Act: 1.7973. Min Act: -0.0000

Data Index: 583947 (C4 (Web Text))

Max Activating Token Index: 928