Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 3596 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 1.8823. Min Range: -1.8823

Max Act: 1.8823. Min Act: -0.0000

Data Index: 57382 (C4 (Web Text))

Max Activating Token Index: 232

Text #1

Max Range: 1.8823. Min Range: -1.8823

Max Act: 1.8013. Min Act: -0.0001

Data Index: 825523 (C4 (Web Text))

Max Activating Token Index: 449

Text #2

Max Range: 1.8823. Min Range: -1.8823

Max Act: 1.7252. Min Act: -0.0001

Data Index: 1311687 (C4 (Web Text))

Max Activating Token Index: 679

Text #3

Max Range: 1.8823. Min Range: -1.8823

Max Act: 1.5632. Min Act: -0.0001

Data Index: 819270 (C4 (Web Text))

Max Activating Token Index: 854

Text #4

Max Range: 1.8823. Min Range: -1.8823

Max Act: 1.6438. Min Act: -0.0001

Data Index: 1208681 (C4 (Web Text))

Max Activating Token Index: 947

Text #5

Max Range: 1.8823. Min Range: -1.8823

Max Act: 1.5577. Min Act: -0.0001

Data Index: 284176 (C4 (Web Text))

Max Activating Token Index: 511

Text #6

Max Range: 1.8823. Min Range: -1.8823

Max Act: 1.4764. Min Act: -0.0001

Data Index: 47596 (C4 (Web Text))

Max Activating Token Index: 28

Text #7

Max Range: 1.8823. Min Range: -1.8823

Max Act: 1.5285. Min Act: -0.0001

Data Index: 1311426 (C4 (Web Text))

Max Activating Token Index: 718

Text #8

Max Range: 1.8823. Min Range: -1.8823

Max Act: 1.5115. Min Act: -0.0001

Data Index: 1096100 (C4 (Web Text))

Max Activating Token Index: 535

Text #9

Max Range: 1.8823. Min Range: -1.8823

Max Act: 1.4616. Min Act: -0.0001

Data Index: 973678 (C4 (Web Text))

Max Activating Token Index: 885

Text #10

Max Range: 1.8823. Min Range: -1.8823

Max Act: 1.5421. Min Act: -0.0001

Data Index: 1106362 (C4 (Web Text))

Max Activating Token Index: 730

Text #11

Max Range: 1.8823. Min Range: -1.8823

Max Act: 1.5636. Min Act: -0.0001

Data Index: 1196181 (C4 (Web Text))

Max Activating Token Index: 678

Text #12

Max Range: 1.8823. Min Range: -1.8823

Max Act: 1.2924. Min Act: -0.0001

Data Index: 1171094 (C4 (Web Text))

Max Activating Token Index: 619

Text #13

Max Range: 1.8823. Min Range: -1.8823

Max Act: 1.4480. Min Act: -0.0001

Data Index: 1341874 (C4 (Web Text))

Max Activating Token Index: 839

Text #14

Max Range: 1.8823. Min Range: -1.8823

Max Act: 1.3518. Min Act: -0.0001

Data Index: 236375 (C4 (Web Text))

Max Activating Token Index: 944

Text #15

Max Range: 1.8823. Min Range: -1.8823

Max Act: 1.3898. Min Act: -0.0001

Data Index: 852971 (C4 (Web Text))

Max Activating Token Index: 211

Text #16

Max Range: 1.8823. Min Range: -1.8823

Max Act: 1.4448. Min Act: -0.0001

Data Index: 1067064 (C4 (Web Text))

Max Activating Token Index: 792

Text #17

Max Range: 1.8823. Min Range: -1.8823

Max Act: 1.3565. Min Act: -0.0001

Data Index: 585186 (C4 (Web Text))

Max Activating Token Index: 573

Text #18

Max Range: 1.8823. Min Range: -1.8823

Max Act: 1.3591. Min Act: -0.0001

Data Index: 603658 (C4 (Web Text))

Max Activating Token Index: 875

Text #19

Max Range: 1.8823. Min Range: -1.8823

Max Act: 1.3837. Min Act: -0.0001

Data Index: 506229 (C4 (Web Text))

Max Activating Token Index: 178