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

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

Neuron 1983 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: 2.2941. Min Range: -2.2941

Max Act: 2.2941. Min Act: -0.0000

Data Index: 542398 (C4 (Web Text))

Max Activating Token Index: 249

Text #1

Max Range: 2.2941. Min Range: -2.2941

Max Act: 2.0590. Min Act: -0.0000

Data Index: 1281614 (C4 (Web Text))

Max Activating Token Index: 193

Text #2

Max Range: 2.2941. Min Range: -2.2941

Max Act: 1.8498. Min Act: -0.0000

Data Index: 43904 (C4 (Web Text))

Max Activating Token Index: 207

Text #3

Max Range: 2.2941. Min Range: -2.2941

Max Act: 1.9459. Min Act: -0.0000

Data Index: 723511 (C4 (Web Text))

Max Activating Token Index: 427

Text #4

Max Range: 2.2941. Min Range: -2.2941

Max Act: 1.8850. Min Act: -0.0000

Data Index: 1309344 (C4 (Web Text))

Max Activating Token Index: 17

Text #5

Max Range: 2.2941. Min Range: -2.2941

Max Act: 1.8272. Min Act: -0.0000

Data Index: 495321 (C4 (Web Text))

Max Activating Token Index: 187

Text #6

Max Range: 2.2941. Min Range: -2.2941

Max Act: 1.7498. Min Act: -0.0000

Data Index: 512710 (C4 (Web Text))

Max Activating Token Index: 129

Text #7

Max Range: 2.2941. Min Range: -2.2941

Max Act: 1.6493. Min Act: -0.0000

Data Index: 403307 (C4 (Web Text))

Max Activating Token Index: 244

Text #8

Max Range: 2.2941. Min Range: -2.2941

Max Act: 1.7243. Min Act: -0.0000

Data Index: 4733 (C4 (Web Text))

Max Activating Token Index: 510

Text #9

Max Range: 2.2941. Min Range: -2.2941

Max Act: 1.5016. Min Act: -0.0000

Data Index: 294239 (C4 (Web Text))

Max Activating Token Index: 343

Text #10

Max Range: 2.2941. Min Range: -2.2941

Max Act: 1.7606. Min Act: -0.0000

Data Index: 500029 (C4 (Web Text))

Max Activating Token Index: 967

Text #11

Max Range: 2.2941. Min Range: -2.2941

Max Act: 1.5786. Min Act: -0.0000

Data Index: 258677 (C4 (Web Text))

Max Activating Token Index: 470

Text #12

Max Range: 2.2941. Min Range: -2.2941

Max Act: 1.5622. Min Act: -0.0000

Data Index: 1061386 (C4 (Web Text))

Max Activating Token Index: 250

Text #13

Max Range: 2.2941. Min Range: -2.2941

Max Act: 1.6510. Min Act: -0.0000

Data Index: 1010977 (C4 (Web Text))

Max Activating Token Index: 37

Text #14

Max Range: 2.2941. Min Range: -2.2941

Max Act: 1.6262. Min Act: -0.0000

Data Index: 839867 (C4 (Web Text))

Max Activating Token Index: 118

Text #15

Max Range: 2.2941. Min Range: -2.2941

Max Act: 1.5205. Min Act: -0.0000

Data Index: 729084 (C4 (Web Text))

Max Activating Token Index: 747

Text #16

Max Range: 2.2941. Min Range: -2.2941

Max Act: 1.6437. Min Act: -0.0000

Data Index: 841033 (C4 (Web Text))

Max Activating Token Index: 20

Text #17

Max Range: 2.2941. Min Range: -2.2941

Max Act: 1.5378. Min Act: -0.0000

Data Index: 1002519 (C4 (Web Text))

Max Activating Token Index: 948

Text #18

Max Range: 2.2941. Min Range: -2.2941

Max Act: 1.5388. Min Act: -0.0000

Data Index: 1074269 (C4 (Web Text))

Max Activating Token Index: 99

Text #19

Max Range: 2.2941. Min Range: -2.2941

Max Act: 1.4608. Min Act: -0.0000

Data Index: 187219 (C4 (Web Text))

Max Activating Token Index: 235