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

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

Neuron 594 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.6041. Min Range: -5.6041

Max Act: 5.6041. Min Act: -0.0000

Data Index: 140790 (C4 (Web Text))

Max Activating Token Index: 720

Text #1

Max Range: 5.6041. Min Range: -5.6041

Max Act: 5.0754. Min Act: -0.0000

Data Index: 1358115 (C4 (Web Text))

Max Activating Token Index: 124

Text #2

Max Range: 5.6041. Min Range: -5.6041

Max Act: 4.8370. Min Act: -0.0000

Data Index: 159984 (C4 (Web Text))

Max Activating Token Index: 167

Text #3

Max Range: 5.6041. Min Range: -5.6041

Max Act: 4.6365. Min Act: -0.0000

Data Index: 521117 (C4 (Web Text))

Max Activating Token Index: 910

Text #4

Max Range: 5.6041. Min Range: -5.6041

Max Act: 4.6276. Min Act: -0.0000

Data Index: 1208729 (C4 (Web Text))

Max Activating Token Index: 894

Text #5

Max Range: 5.6041. Min Range: -5.6041

Max Act: 4.8000. Min Act: -0.0000

Data Index: 882770 (C4 (Web Text))

Max Activating Token Index: 163

Text #6

Max Range: 5.6041. Min Range: -5.6041

Max Act: 4.5177. Min Act: -0.0000

Data Index: 460006 (C4 (Web Text))

Max Activating Token Index: 719

Text #7

Max Range: 5.6041. Min Range: -5.6041

Max Act: 4.4845. Min Act: -0.0000

Data Index: 773473 (C4 (Web Text))

Max Activating Token Index: 280

Text #8

Max Range: 5.6041. Min Range: -5.6041

Max Act: 4.6264. Min Act: -0.0000

Data Index: 1336990 (C4 (Web Text))

Max Activating Token Index: 804

Text #9

Max Range: 5.6041. Min Range: -5.6041

Max Act: 4.2330. Min Act: -0.0000

Data Index: 867812 (C4 (Web Text))

Max Activating Token Index: 384

Text #10

Max Range: 5.6041. Min Range: -5.6041

Max Act: 4.3531. Min Act: -0.0000

Data Index: 1150005 (C4 (Web Text))

Max Activating Token Index: 840

Text #11

Max Range: 5.6041. Min Range: -5.6041

Max Act: 4.3215. Min Act: -0.0000

Data Index: 669004 (C4 (Web Text))

Max Activating Token Index: 982

Text #12

Max Range: 5.6041. Min Range: -5.6041

Max Act: 4.2548. Min Act: -0.0000

Data Index: 508049 (C4 (Web Text))

Max Activating Token Index: 813

Text #13

Max Range: 5.6041. Min Range: -5.6041

Max Act: 4.5713. Min Act: -0.0000

Data Index: 810686 (C4 (Web Text))

Max Activating Token Index: 723

Text #14

Max Range: 5.6041. Min Range: -5.6041

Max Act: 4.1595. Min Act: -0.0000

Data Index: 733715 (C4 (Web Text))

Max Activating Token Index: 29

Text #15

Max Range: 5.6041. Min Range: -5.6041

Max Act: 4.1110. Min Act: -0.0000

Data Index: 1346609 (C4 (Web Text))

Max Activating Token Index: 905

Text #16

Max Range: 5.6041. Min Range: -5.6041

Max Act: 4.0135. Min Act: -0.0000

Data Index: 297732 (C4 (Web Text))

Max Activating Token Index: 480

Text #17

Max Range: 5.6041. Min Range: -5.6041

Max Act: 3.8075. Min Act: -0.0000

Data Index: 1003202 (C4 (Web Text))

Max Activating Token Index: 213

Text #18

Max Range: 5.6041. Min Range: -5.6041

Max Act: 3.9821. Min Act: -0.0000

Data Index: 112318 (C4 (Web Text))

Max Activating Token Index: 430

Text #19

Max Range: 5.6041. Min Range: -5.6041

Max Act: 3.7617. Min Act: -0.0000

Data Index: 1095226 (C4 (Web Text))

Max Activating Token Index: 746