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

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

Neuron 882 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: 1.6995. Min Range: -1.6995

Max Act: 1.6995. Min Act: -0.0000

Data Index: 880107 (C4 (Web Text))

Max Activating Token Index: 703

Text #1

Max Range: 1.6995. Min Range: -1.6995

Max Act: 1.5325. Min Act: -0.0000

Data Index: 427417 (C4 (Web Text))

Max Activating Token Index: 848

Text #2

Max Range: 1.6995. Min Range: -1.6995

Max Act: 1.3522. Min Act: -0.0000

Data Index: 1057808 (C4 (Web Text))

Max Activating Token Index: 377

Text #3

Max Range: 1.6995. Min Range: -1.6995

Max Act: 1.3829. Min Act: -0.0000

Data Index: 198098 (C4 (Web Text))

Max Activating Token Index: 253

Text #4

Max Range: 1.6995. Min Range: -1.6995

Max Act: 1.2803. Min Act: -0.0000

Data Index: 1253922 (C4 (Web Text))

Max Activating Token Index: 943

Text #5

Max Range: 1.6995. Min Range: -1.6995

Max Act: 1.3005. Min Act: -0.0000

Data Index: 873772 (C4 (Web Text))

Max Activating Token Index: 674

Text #6

Max Range: 1.6995. Min Range: -1.6995

Max Act: 1.2426. Min Act: -0.0000

Data Index: 337124 (C4 (Web Text))

Max Activating Token Index: 716

Text #7

Max Range: 1.6995. Min Range: -1.6995

Max Act: 1.2857. Min Act: -0.0000

Data Index: 738687 (C4 (Web Text))

Max Activating Token Index: 443

Text #8

Max Range: 1.6995. Min Range: -1.6995

Max Act: 1.2100. Min Act: -0.0000

Data Index: 509494 (C4 (Web Text))

Max Activating Token Index: 839

Text #9

Max Range: 1.6995. Min Range: -1.6995

Max Act: 1.2619. Min Act: -0.0000

Data Index: 920996 (C4 (Web Text))

Max Activating Token Index: 368

Text #10

Max Range: 1.6995. Min Range: -1.6995

Max Act: 1.2211. Min Act: -0.0000

Data Index: 1055215 (C4 (Web Text))

Max Activating Token Index: 760

Text #11

Max Range: 1.6995. Min Range: -1.6995

Max Act: 1.2500. Min Act: -0.0000

Data Index: 1151636 (C4 (Web Text))

Max Activating Token Index: 353

Text #12

Max Range: 1.6995. Min Range: -1.6995

Max Act: 1.2429. Min Act: -0.0000

Data Index: 1261012 (C4 (Web Text))

Max Activating Token Index: 936

Text #13

Max Range: 1.6995. Min Range: -1.6995

Max Act: 1.2368. Min Act: -0.0000

Data Index: 675833 (C4 (Web Text))

Max Activating Token Index: 568

Text #14

Max Range: 1.6995. Min Range: -1.6995

Max Act: 1.2614. Min Act: -0.0000

Data Index: 995034 (C4 (Web Text))

Max Activating Token Index: 332

Text #15

Max Range: 1.6995. Min Range: -1.6995

Max Act: 1.1356. Min Act: -0.0000

Data Index: 947656 (C4 (Web Text))

Max Activating Token Index: 181

Text #16

Max Range: 1.6995. Min Range: -1.6995

Max Act: 1.2136. Min Act: -0.0000

Data Index: 942368 (C4 (Web Text))

Max Activating Token Index: 377

Text #17

Max Range: 1.6995. Min Range: -1.6995

Max Act: 1.2455. Min Act: -0.0000

Data Index: 688633 (C4 (Web Text))

Max Activating Token Index: 282

Text #18

Max Range: 1.6995. Min Range: -1.6995

Max Act: 1.1968. Min Act: -0.0000

Data Index: 1337524 (C4 (Web Text))

Max Activating Token Index: 80

Text #19

Max Range: 1.6995. Min Range: -1.6995

Max Act: 1.2093. Min Act: -0.0000

Data Index: 133368 (C4 (Web Text))

Max Activating Token Index: 267