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

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

Neuron 771 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3634. Min Range: -0.3634

Max Act: 0.3634. Min Act: -0.0000

Data Index: 615458 (C4 (Web Text))

Max Activating Token Index: 506

Text #1

Max Range: 0.3634. Min Range: -0.3634

Max Act: 0.3415. Min Act: -0.0000

Data Index: 285262 (C4 (Web Text))

Max Activating Token Index: 715

Text #2

Max Range: 0.3634. Min Range: -0.3634

Max Act: 0.3353. Min Act: -0.0000

Data Index: 422481 (C4 (Web Text))

Max Activating Token Index: 1018

Text #3

Max Range: 0.3634. Min Range: -0.3634

Max Act: 0.3359. Min Act: -0.0000

Data Index: 690336 (C4 (Web Text))

Max Activating Token Index: 86

Text #4

Max Range: 0.3634. Min Range: -0.3634

Max Act: 0.3466. Min Act: -0.0000

Data Index: 1240779 (C4 (Web Text))

Max Activating Token Index: 751

Text #5

Max Range: 0.3634. Min Range: -0.3634

Max Act: 0.3220. Min Act: -0.0000

Data Index: 375827 (C4 (Web Text))

Max Activating Token Index: 172

Text #6

Max Range: 0.3634. Min Range: -0.3634

Max Act: 0.3202. Min Act: -0.0001

Data Index: 653691 (C4 (Web Text))

Max Activating Token Index: 400

Text #7

Max Range: 0.3634. Min Range: -0.3634

Max Act: 0.2944. Min Act: -0.0000

Data Index: 36434 (C4 (Web Text))

Max Activating Token Index: 485

Text #8

Max Range: 0.3634. Min Range: -0.3634

Max Act: 0.3183. Min Act: -0.0000

Data Index: 1104259 (C4 (Web Text))

Max Activating Token Index: 883

Text #9

Max Range: 0.3634. Min Range: -0.3634

Max Act: 0.3119. Min Act: -0.0001

Data Index: 340542 (C4 (Web Text))

Max Activating Token Index: 778

Text #10

Max Range: 0.3634. Min Range: -0.3634

Max Act: 0.3128. Min Act: -0.0000

Data Index: 517695 (C4 (Web Text))

Max Activating Token Index: 811

Text #11

Max Range: 0.3634. Min Range: -0.3634

Max Act: 0.2949. Min Act: -0.0000

Data Index: 443421 (C4 (Web Text))

Max Activating Token Index: 960

Text #12

Max Range: 0.3634. Min Range: -0.3634

Max Act: 0.3154. Min Act: -0.0000

Data Index: 1201810 (C4 (Web Text))

Max Activating Token Index: 675

Text #13

Max Range: 0.3634. Min Range: -0.3634

Max Act: 0.3069. Min Act: -0.0000

Data Index: 530764 (C4 (Web Text))

Max Activating Token Index: 749

Text #14

Max Range: 0.3634. Min Range: -0.3634

Max Act: 0.2647. Min Act: -0.0000

Data Index: 1015862 (C4 (Web Text))

Max Activating Token Index: 697

Text #15

Max Range: 0.3634. Min Range: -0.3634

Max Act: 0.2845. Min Act: -0.0000

Data Index: 689092 (C4 (Web Text))

Max Activating Token Index: 419

Text #16

Max Range: 0.3634. Min Range: -0.3634

Max Act: 0.2830. Min Act: -0.0000

Data Index: 1188875 (C4 (Web Text))

Max Activating Token Index: 269

Text #17

Max Range: 0.3634. Min Range: -0.3634

Max Act: 0.3045. Min Act: -0.0000

Data Index: 176266 (C4 (Web Text))

Max Activating Token Index: 527

Text #18

Max Range: 0.3634. Min Range: -0.3634

Max Act: 0.2724. Min Act: -0.0000

Data Index: 527249 (C4 (Web Text))

Max Activating Token Index: 132

Text #19

Max Range: 0.3634. Min Range: -0.3634

Max Act: 0.2722. Min Act: -0.0000

Data Index: 258536 (C4 (Web Text))

Max Activating Token Index: 863