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

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

Neuron 4193 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.8059. Min Range: -4.8059

Max Act: 4.8059. Min Act: -0.0000

Data Index: 772630 (C4 (Web Text))

Max Activating Token Index: 807

Text #1

Max Range: 4.8059. Min Range: -4.8059

Max Act: 4.3928. Min Act: -0.0000

Data Index: 1172942 (C4 (Web Text))

Max Activating Token Index: 956

Text #2

Max Range: 4.8059. Min Range: -4.8059

Max Act: 4.3516. Min Act: -0.0000

Data Index: 246196 (C4 (Web Text))

Max Activating Token Index: 262

Text #3

Max Range: 4.8059. Min Range: -4.8059

Max Act: 4.6604. Min Act: -0.0000

Data Index: 521023 (C4 (Web Text))

Max Activating Token Index: 529

Text #4

Max Range: 4.8059. Min Range: -4.8059

Max Act: 4.4090. Min Act: -0.0000

Data Index: 1210712 (C4 (Web Text))

Max Activating Token Index: 453

Text #5

Max Range: 4.8059. Min Range: -4.8059

Max Act: 4.2325. Min Act: -0.0000

Data Index: 763870 (C4 (Web Text))

Max Activating Token Index: 734

Text #6

Max Range: 4.8059. Min Range: -4.8059

Max Act: 3.8286. Min Act: -0.0000

Data Index: 451897 (C4 (Web Text))

Max Activating Token Index: 582

Text #7

Max Range: 4.8059. Min Range: -4.8059

Max Act: 4.2735. Min Act: -0.0000

Data Index: 98588 (C4 (Web Text))

Max Activating Token Index: 498

Text #8

Max Range: 4.8059. Min Range: -4.8059

Max Act: 3.6686. Min Act: -0.0000

Data Index: 316495 (C4 (Web Text))

Max Activating Token Index: 79

Text #9

Max Range: 4.8059. Min Range: -4.8059

Max Act: 4.0054. Min Act: -0.0000

Data Index: 315121 (C4 (Web Text))

Max Activating Token Index: 697

Text #10

Max Range: 4.8059. Min Range: -4.8059

Max Act: 4.1212. Min Act: -0.0000

Data Index: 941938 (C4 (Web Text))

Max Activating Token Index: 116

Text #11

Max Range: 4.8059. Min Range: -4.8059

Max Act: 3.8035. Min Act: -0.0000

Data Index: 421577 (C4 (Web Text))

Max Activating Token Index: 43

Text #12

Max Range: 4.8059. Min Range: -4.8059

Max Act: 3.7990. Min Act: -0.0000

Data Index: 486855 (C4 (Web Text))

Max Activating Token Index: 40

Text #13

Max Range: 4.8059. Min Range: -4.8059

Max Act: 3.7419. Min Act: -0.0000

Data Index: 188982 (C4 (Web Text))

Max Activating Token Index: 19

Text #14

Max Range: 4.8059. Min Range: -4.8059

Max Act: 3.9310. Min Act: -0.0000

Data Index: 656621 (C4 (Web Text))

Max Activating Token Index: 895

Text #15

Max Range: 4.8059. Min Range: -4.8059

Max Act: 3.9389. Min Act: -0.0000

Data Index: 495850 (C4 (Web Text))

Max Activating Token Index: 701

Text #16

Max Range: 4.8059. Min Range: -4.8059

Max Act: 4.0729. Min Act: -0.0000

Data Index: 1012345 (C4 (Web Text))

Max Activating Token Index: 1019

Text #17

Max Range: 4.8059. Min Range: -4.8059

Max Act: 4.0617. Min Act: -0.0000

Data Index: 983183 (C4 (Web Text))

Max Activating Token Index: 117

Text #18

Max Range: 4.8059. Min Range: -4.8059

Max Act: 4.0100. Min Act: -0.0000

Data Index: 1337928 (C4 (Web Text))

Max Activating Token Index: 267

Text #19

Max Range: 4.8059. Min Range: -4.8059

Max Act: 3.4855. Min Act: -0.0000

Data Index: 827083 (C4 (Web Text))

Max Activating Token Index: 236