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

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

Neuron 836 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: 1.6173. Min Range: -1.6173

Max Act: 1.5390. Min Act: -0.0000

Data Index: 806880 (C4 (Web Text))

Max Activating Token Index: 545

Text #1

Max Range: 1.6173. Min Range: -1.6173

Max Act: 1.6173. Min Act: -0.0000

Data Index: 223441 (C4 (Web Text))

Max Activating Token Index: 750

Text #2

Max Range: 1.6173. Min Range: -1.6173

Max Act: 1.5163. Min Act: -0.0000

Data Index: 1181185 (C4 (Web Text))

Max Activating Token Index: 645

Text #3

Max Range: 1.6173. Min Range: -1.6173

Max Act: 1.4684. Min Act: -0.0000

Data Index: 483722 (C4 (Web Text))

Max Activating Token Index: 537

Text #4

Max Range: 1.6173. Min Range: -1.6173

Max Act: 1.5562. Min Act: -0.0000

Data Index: 720596 (C4 (Web Text))

Max Activating Token Index: 596

Text #5

Max Range: 1.6173. Min Range: -1.6173

Max Act: 1.4251. Min Act: -0.0000

Data Index: 1128103 (C4 (Web Text))

Max Activating Token Index: 965

Text #6

Max Range: 1.6173. Min Range: -1.6173

Max Act: 1.4445. Min Act: -0.0000

Data Index: 104844 (C4 (Web Text))

Max Activating Token Index: 865

Text #7

Max Range: 1.6173. Min Range: -1.6173

Max Act: 1.4847. Min Act: -0.0000

Data Index: 853179 (C4 (Web Text))

Max Activating Token Index: 648

Text #8

Max Range: 1.6173. Min Range: -1.6173

Max Act: 1.4401. Min Act: -0.0000

Data Index: 325573 (C4 (Web Text))

Max Activating Token Index: 744

Text #9

Max Range: 1.6173. Min Range: -1.6173

Max Act: 1.4211. Min Act: -0.0000

Data Index: 787956 (C4 (Web Text))

Max Activating Token Index: 601

Text #10

Max Range: 1.6173. Min Range: -1.6173

Max Act: 1.4601. Min Act: -0.0000

Data Index: 113167 (C4 (Web Text))

Max Activating Token Index: 930

Text #11

Max Range: 1.6173. Min Range: -1.6173

Max Act: 1.4762. Min Act: -0.0000

Data Index: 933335 (C4 (Web Text))

Max Activating Token Index: 797

Text #12

Max Range: 1.6173. Min Range: -1.6173

Max Act: 1.4123. Min Act: -0.0000

Data Index: 782979 (C4 (Web Text))

Max Activating Token Index: 760

Text #13

Max Range: 1.6173. Min Range: -1.6173

Max Act: 1.4652. Min Act: -0.0000

Data Index: 379728 (C4 (Web Text))

Max Activating Token Index: 558

Text #14

Max Range: 1.6173. Min Range: -1.6173

Max Act: 1.4459. Min Act: -0.0000

Data Index: 322992 (C4 (Web Text))

Max Activating Token Index: 739

Text #15

Max Range: 1.6173. Min Range: -1.6173

Max Act: 1.4168. Min Act: -0.0000

Data Index: 47265 (C4 (Web Text))

Max Activating Token Index: 751

Text #16

Max Range: 1.6173. Min Range: -1.6173

Max Act: 1.5112. Min Act: -0.0000

Data Index: 735187 (C4 (Web Text))

Max Activating Token Index: 240

Text #17

Max Range: 1.6173. Min Range: -1.6173

Max Act: 1.4111. Min Act: -0.0000

Data Index: 170551 (C4 (Web Text))

Max Activating Token Index: 183

Text #18

Max Range: 1.6173. Min Range: -1.6173

Max Act: 1.4494. Min Act: -0.0000

Data Index: 1315512 (C4 (Web Text))

Max Activating Token Index: 530

Text #19

Max Range: 1.6173. Min Range: -1.6173

Max Act: 1.4970. Min Act: -0.0000

Data Index: 158263 (C4 (Web Text))

Max Activating Token Index: 757