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

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

Neuron 3009 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.4787. Min Range: -4.4787

Max Act: 4.4787. Min Act: -0.0000

Data Index: 910973 (C4 (Web Text))

Max Activating Token Index: 151

Text #1

Max Range: 4.4787. Min Range: -4.4787

Max Act: 4.2884. Min Act: -0.0000

Data Index: 1102005 (C4 (Web Text))

Max Activating Token Index: 127

Text #2

Max Range: 4.4787. Min Range: -4.4787

Max Act: 4.2809. Min Act: 0.0000

Data Index: 913417 (C4 (Web Text))

Max Activating Token Index: 686

Text #3

Max Range: 4.4787. Min Range: -4.4787

Max Act: 3.9208. Min Act: -0.0000

Data Index: 762369 (C4 (Web Text))

Max Activating Token Index: 855

Text #4

Max Range: 4.4787. Min Range: -4.4787

Max Act: 3.6161. Min Act: -0.0000

Data Index: 988103 (C4 (Web Text))

Max Activating Token Index: 810

Text #5

Max Range: 4.4787. Min Range: -4.4787

Max Act: 3.4412. Min Act: -0.0000

Data Index: 1548188 (Python Code)

Max Activating Token Index: 915

Text #6

Max Range: 4.4787. Min Range: -4.4787

Max Act: 3.5495. Min Act: 0.0000

Data Index: 857497 (C4 (Web Text))

Max Activating Token Index: 562

Text #7

Max Range: 4.4787. Min Range: -4.4787

Max Act: 3.2169. Min Act: -0.0000

Data Index: 1410356 (Python Code)

Max Activating Token Index: 181

Text #8

Max Range: 4.4787. Min Range: -4.4787

Max Act: 3.0172. Min Act: -0.0000

Data Index: 1052105 (C4 (Web Text))

Max Activating Token Index: 692

Text #9

Max Range: 4.4787. Min Range: -4.4787

Max Act: 2.8637. Min Act: -0.0000

Data Index: 1618341 (Python Code)

Max Activating Token Index: 15

Text #10

Max Range: 4.4787. Min Range: -4.4787

Max Act: 2.9823. Min Act: -0.0000

Data Index: 1543313 (Python Code)

Max Activating Token Index: 183

Text #11

Max Range: 4.4787. Min Range: -4.4787

Max Act: 2.6696. Min Act: 0.0000

Data Index: 1255407 (C4 (Web Text))

Max Activating Token Index: 681

Text #12

Max Range: 4.4787. Min Range: -4.4787

Max Act: 3.0571. Min Act: -0.0000

Data Index: 416640 (C4 (Web Text))

Max Activating Token Index: 760

Text #13

Max Range: 4.4787. Min Range: -4.4787

Max Act: 2.6220. Min Act: -0.0000

Data Index: 1138031 (C4 (Web Text))

Max Activating Token Index: 859

Text #14

Max Range: 4.4787. Min Range: -4.4787

Max Act: 2.8927. Min Act: -0.0000

Data Index: 477130 (C4 (Web Text))

Max Activating Token Index: 638

Text #15

Max Range: 4.4787. Min Range: -4.4787

Max Act: 2.8461. Min Act: -0.0000

Data Index: 217981 (C4 (Web Text))

Max Activating Token Index: 938

Text #16

Max Range: 4.4787. Min Range: -4.4787

Max Act: 2.8558. Min Act: -0.0000

Data Index: 248604 (C4 (Web Text))

Max Activating Token Index: 527

Text #17

Max Range: 4.4787. Min Range: -4.4787

Max Act: 2.6144. Min Act: 0.0000

Data Index: 850717 (C4 (Web Text))

Max Activating Token Index: 186

Text #18

Max Range: 4.4787. Min Range: -4.4787

Max Act: 2.4887. Min Act: -0.0000

Data Index: 225796 (C4 (Web Text))

Max Activating Token Index: 324

Text #19

Max Range: 4.4787. Min Range: -4.4787

Max Act: 2.6099. Min Act: 0.0000

Data Index: 343858 (C4 (Web Text))

Max Activating Token Index: 514