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

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

Neuron 1029 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.7740. Min Range: -2.7740

Max Act: 2.7740. Min Act: -0.0000

Data Index: 735686 (C4 (Web Text))

Max Activating Token Index: 638

Text #1

Max Range: 2.7740. Min Range: -2.7740

Max Act: 2.7479. Min Act: -0.0000

Data Index: 590818 (C4 (Web Text))

Max Activating Token Index: 702

Text #2

Max Range: 2.7740. Min Range: -2.7740

Max Act: 2.5193. Min Act: -0.0000

Data Index: 279238 (C4 (Web Text))

Max Activating Token Index: 783

Text #3

Max Range: 2.7740. Min Range: -2.7740

Max Act: 2.3178. Min Act: -0.0000

Data Index: 987774 (C4 (Web Text))

Max Activating Token Index: 752

Text #4

Max Range: 2.7740. Min Range: -2.7740

Max Act: 2.3850. Min Act: -0.0000

Data Index: 446067 (C4 (Web Text))

Max Activating Token Index: 390

Text #5

Max Range: 2.7740. Min Range: -2.7740

Max Act: 2.3725. Min Act: -0.0000

Data Index: 969944 (C4 (Web Text))

Max Activating Token Index: 528

Text #6

Max Range: 2.7740. Min Range: -2.7740

Max Act: 2.2119. Min Act: -0.0000

Data Index: 2988 (C4 (Web Text))

Max Activating Token Index: 338

Text #7

Max Range: 2.7740. Min Range: -2.7740

Max Act: 2.4180. Min Act: -0.0000

Data Index: 920204 (C4 (Web Text))

Max Activating Token Index: 906

Text #8

Max Range: 2.7740. Min Range: -2.7740

Max Act: 2.2560. Min Act: -0.0000

Data Index: 609254 (C4 (Web Text))

Max Activating Token Index: 952

Text #9

Max Range: 2.7740. Min Range: -2.7740

Max Act: 2.2566. Min Act: -0.0000

Data Index: 895790 (C4 (Web Text))

Max Activating Token Index: 100

Text #10

Max Range: 2.7740. Min Range: -2.7740

Max Act: 2.1330. Min Act: -0.0000

Data Index: 1358763 (C4 (Web Text))

Max Activating Token Index: 26

Text #11

Max Range: 2.7740. Min Range: -2.7740

Max Act: 2.1270. Min Act: -0.0000

Data Index: 885574 (C4 (Web Text))

Max Activating Token Index: 906

Text #12

Max Range: 2.7740. Min Range: -2.7740

Max Act: 2.3387. Min Act: -0.0000

Data Index: 962693 (C4 (Web Text))

Max Activating Token Index: 501

Text #13

Max Range: 2.7740. Min Range: -2.7740

Max Act: 2.3434. Min Act: -0.0000

Data Index: 19935 (C4 (Web Text))

Max Activating Token Index: 125

Text #14

Max Range: 2.7740. Min Range: -2.7740

Max Act: 2.0715. Min Act: -0.0000

Data Index: 1207481 (C4 (Web Text))

Max Activating Token Index: 814

Text #15

Max Range: 2.7740. Min Range: -2.7740

Max Act: 2.1968. Min Act: -0.0000

Data Index: 499926 (C4 (Web Text))

Max Activating Token Index: 76

Text #16

Max Range: 2.7740. Min Range: -2.7740

Max Act: 2.0821. Min Act: -0.0000

Data Index: 1332045 (C4 (Web Text))

Max Activating Token Index: 766

Text #17

Max Range: 2.7740. Min Range: -2.7740

Max Act: 1.9642. Min Act: -0.0000

Data Index: 339664 (C4 (Web Text))

Max Activating Token Index: 954

Text #18

Max Range: 2.7740. Min Range: -2.7740

Max Act: 2.0585. Min Act: -0.0000

Data Index: 597809 (C4 (Web Text))

Max Activating Token Index: 938

Text #19

Max Range: 2.7740. Min Range: -2.7740

Max Act: 2.0505. Min Act: -0.0000

Data Index: 549258 (C4 (Web Text))

Max Activating Token Index: 1004