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

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

Neuron 5575 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.2053. Min Range: -1.2053

Max Act: 1.2053. Min Act: -0.0000

Data Index: 70499 (C4 (Web Text))

Max Activating Token Index: 374

Text #1

Max Range: 1.2053. Min Range: -1.2053

Max Act: 1.0767. Min Act: -0.0001

Data Index: 729311 (C4 (Web Text))

Max Activating Token Index: 173

Text #2

Max Range: 1.2053. Min Range: -1.2053

Max Act: 0.9343. Min Act: -0.0000

Data Index: 198047 (C4 (Web Text))

Max Activating Token Index: 522

Text #3

Max Range: 1.2053. Min Range: -1.2053

Max Act: 0.9680. Min Act: -0.0000

Data Index: 987899 (C4 (Web Text))

Max Activating Token Index: 718

Text #4

Max Range: 1.2053. Min Range: -1.2053

Max Act: 0.9733. Min Act: -0.0000

Data Index: 1089771 (C4 (Web Text))

Max Activating Token Index: 460

Text #5

Max Range: 1.2053. Min Range: -1.2053

Max Act: 0.8988. Min Act: -0.0000

Data Index: 1116962 (C4 (Web Text))

Max Activating Token Index: 108

Text #6

Max Range: 1.2053. Min Range: -1.2053

Max Act: 0.9018. Min Act: -0.0001

Data Index: 1312120 (C4 (Web Text))

Max Activating Token Index: 661

Text #7

Max Range: 1.2053. Min Range: -1.2053

Max Act: 0.8486. Min Act: -0.0000

Data Index: 844717 (C4 (Web Text))

Max Activating Token Index: 24

Text #8

Max Range: 1.2053. Min Range: -1.2053

Max Act: 0.8509. Min Act: -0.0000

Data Index: 255873 (C4 (Web Text))

Max Activating Token Index: 718

Text #9

Max Range: 1.2053. Min Range: -1.2053

Max Act: 0.8428. Min Act: -0.0000

Data Index: 653586 (C4 (Web Text))

Max Activating Token Index: 137

Text #10

Max Range: 1.2053. Min Range: -1.2053

Max Act: 0.8468. Min Act: -0.0000

Data Index: 270277 (C4 (Web Text))

Max Activating Token Index: 855

Text #11

Max Range: 1.2053. Min Range: -1.2053

Max Act: 0.8137. Min Act: -0.0000

Data Index: 1189867 (C4 (Web Text))

Max Activating Token Index: 652

Text #12

Max Range: 1.2053. Min Range: -1.2053

Max Act: 0.8188. Min Act: -0.0000

Data Index: 526544 (C4 (Web Text))

Max Activating Token Index: 582

Text #13

Max Range: 1.2053. Min Range: -1.2053

Max Act: 0.8200. Min Act: -0.0000

Data Index: 940909 (C4 (Web Text))

Max Activating Token Index: 651

Text #14

Max Range: 1.2053. Min Range: -1.2053

Max Act: 0.7915. Min Act: -0.0000

Data Index: 452335 (C4 (Web Text))

Max Activating Token Index: 91

Text #15

Max Range: 1.2053. Min Range: -1.2053

Max Act: 0.7910. Min Act: -0.0000

Data Index: 650390 (C4 (Web Text))

Max Activating Token Index: 665

Text #16

Max Range: 1.2053. Min Range: -1.2053

Max Act: 0.8109. Min Act: -0.0000

Data Index: 1319793 (C4 (Web Text))

Max Activating Token Index: 1002

Text #17

Max Range: 1.2053. Min Range: -1.2053

Max Act: 0.7499. Min Act: -0.0000

Data Index: 1256332 (C4 (Web Text))

Max Activating Token Index: 565

Text #18

Max Range: 1.2053. Min Range: -1.2053

Max Act: 0.7793. Min Act: -0.0000

Data Index: 360160 (C4 (Web Text))

Max Activating Token Index: 788

Text #19

Max Range: 1.2053. Min Range: -1.2053

Max Act: 0.8004. Min Act: -0.0000

Data Index: 813250 (C4 (Web Text))

Max Activating Token Index: 215