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

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

Neuron 5441 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.5217. Min Range: -3.5217

Max Act: 3.5217. Min Act: -0.0001

Data Index: 1130400 (C4 (Web Text))

Max Activating Token Index: 20

Text #1

Max Range: 3.5217. Min Range: -3.5217

Max Act: 3.0601. Min Act: -0.0001

Data Index: 1017085 (C4 (Web Text))

Max Activating Token Index: 802

Text #2

Max Range: 3.5217. Min Range: -3.5217

Max Act: 2.8879. Min Act: -0.0001

Data Index: 411095 (C4 (Web Text))

Max Activating Token Index: 939

Text #3

Max Range: 3.5217. Min Range: -3.5217

Max Act: 2.9295. Min Act: -0.0001

Data Index: 541900 (C4 (Web Text))

Max Activating Token Index: 510

Text #4

Max Range: 3.5217. Min Range: -3.5217

Max Act: 2.6626. Min Act: -0.0001

Data Index: 538634 (C4 (Web Text))

Max Activating Token Index: 995

Text #5

Max Range: 3.5217. Min Range: -3.5217

Max Act: 2.5291. Min Act: -0.0001

Data Index: 627435 (C4 (Web Text))

Max Activating Token Index: 523

Text #6

Max Range: 3.5217. Min Range: -3.5217

Max Act: 2.9208. Min Act: -0.0001

Data Index: 504854 (C4 (Web Text))

Max Activating Token Index: 666

Text #7

Max Range: 3.5217. Min Range: -3.5217

Max Act: 2.6021. Min Act: -0.0001

Data Index: 955103 (C4 (Web Text))

Max Activating Token Index: 7

Text #8

Max Range: 3.5217. Min Range: -3.5217

Max Act: 2.5118. Min Act: -0.0001

Data Index: 159774 (C4 (Web Text))

Max Activating Token Index: 221

Text #9

Max Range: 3.5217. Min Range: -3.5217

Max Act: 2.5231. Min Act: -0.0001

Data Index: 997230 (C4 (Web Text))

Max Activating Token Index: 10

Text #10

Max Range: 3.5217. Min Range: -3.5217

Max Act: 2.8851. Min Act: -0.0001

Data Index: 1322209 (C4 (Web Text))

Max Activating Token Index: 748

Text #11

Max Range: 3.5217. Min Range: -3.5217

Max Act: 2.7758. Min Act: -0.0001

Data Index: 1299592 (C4 (Web Text))

Max Activating Token Index: 122

Text #12

Max Range: 3.5217. Min Range: -3.5217

Max Act: 2.3798. Min Act: -0.0001

Data Index: 121221 (C4 (Web Text))

Max Activating Token Index: 98

Text #13

Max Range: 3.5217. Min Range: -3.5217

Max Act: 2.3271. Min Act: -0.0001

Data Index: 639354 (C4 (Web Text))

Max Activating Token Index: 898

Text #14

Max Range: 3.5217. Min Range: -3.5217

Max Act: 2.6965. Min Act: -0.0001

Data Index: 652734 (C4 (Web Text))

Max Activating Token Index: 468

Text #15

Max Range: 3.5217. Min Range: -3.5217

Max Act: 2.1894. Min Act: -0.0001

Data Index: 675737 (C4 (Web Text))

Max Activating Token Index: 39

Text #16

Max Range: 3.5217. Min Range: -3.5217

Max Act: 1.9598. Min Act: -0.0001

Data Index: 255134 (C4 (Web Text))

Max Activating Token Index: 190

Text #17

Max Range: 3.5217. Min Range: -3.5217

Max Act: 2.3918. Min Act: -0.0001

Data Index: 148184 (C4 (Web Text))

Max Activating Token Index: 137

Text #18

Max Range: 3.5217. Min Range: -3.5217

Max Act: 2.2515. Min Act: -0.0001

Data Index: 1216401 (C4 (Web Text))

Max Activating Token Index: 110

Text #19

Max Range: 3.5217. Min Range: -3.5217

Max Act: 2.3502. Min Act: -0.0001

Data Index: 724746 (C4 (Web Text))

Max Activating Token Index: 340