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

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

Neuron 130 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: 0.3189. Min Range: -0.3189

Max Act: 0.3189. Min Act: -0.0001

Data Index: 34620 (C4 (Web Text))

Max Activating Token Index: 23

Text #1

Max Range: 0.3189. Min Range: -0.3189

Max Act: 0.1713. Min Act: -0.0000

Data Index: 958890 (C4 (Web Text))

Max Activating Token Index: 928

Text #2

Max Range: 0.3189. Min Range: -0.3189

Max Act: 0.1378. Min Act: -0.0001

Data Index: 783404 (C4 (Web Text))

Max Activating Token Index: 572

Text #3

Max Range: 0.3189. Min Range: -0.3189

Max Act: 0.1005. Min Act: -0.0001

Data Index: 393677 (C4 (Web Text))

Max Activating Token Index: 799

Text #4

Max Range: 0.3189. Min Range: -0.3189

Max Act: 0.1097. Min Act: -0.0001

Data Index: 473252 (C4 (Web Text))

Max Activating Token Index: 104

Text #5

Max Range: 0.3189. Min Range: -0.3189

Max Act: 0.1169. Min Act: -0.0001

Data Index: 125373 (C4 (Web Text))

Max Activating Token Index: 1008

Text #6

Max Range: 0.3189. Min Range: -0.3189

Max Act: 0.0948. Min Act: -0.0001

Data Index: 306108 (C4 (Web Text))

Max Activating Token Index: 443

Text #7

Max Range: 0.3189. Min Range: -0.3189

Max Act: 0.1042. Min Act: -0.0001

Data Index: 388195 (C4 (Web Text))

Max Activating Token Index: 437

Text #8

Max Range: 0.3189. Min Range: -0.3189

Max Act: 0.0937. Min Act: -0.0001

Data Index: 1149142 (C4 (Web Text))

Max Activating Token Index: 256

Text #9

Max Range: 0.3189. Min Range: -0.3189

Max Act: 0.1065. Min Act: -0.0001

Data Index: 1150850 (C4 (Web Text))

Max Activating Token Index: 718

Text #10

Max Range: 0.3189. Min Range: -0.3189

Max Act: 0.0842. Min Act: -0.0001

Data Index: 561325 (C4 (Web Text))

Max Activating Token Index: 931

Text #11

Max Range: 0.3189. Min Range: -0.3189

Max Act: 0.0837. Min Act: -0.0001

Data Index: 194936 (C4 (Web Text))

Max Activating Token Index: 53

Text #12

Max Range: 0.3189. Min Range: -0.3189

Max Act: 0.0700. Min Act: -0.0001

Data Index: 902121 (C4 (Web Text))

Max Activating Token Index: 797

Text #13

Max Range: 0.3189. Min Range: -0.3189

Max Act: 0.0754. Min Act: -0.0001

Data Index: 889190 (C4 (Web Text))

Max Activating Token Index: 795

Text #14

Max Range: 0.3189. Min Range: -0.3189

Max Act: 0.0753. Min Act: -0.0001

Data Index: 677774 (C4 (Web Text))

Max Activating Token Index: 863

Text #15

Max Range: 0.3189. Min Range: -0.3189

Max Act: 0.0723. Min Act: -0.0001

Data Index: 1224579 (C4 (Web Text))

Max Activating Token Index: 435

Text #16

Max Range: 0.3189. Min Range: -0.3189

Max Act: 0.0693. Min Act: -0.0001

Data Index: 1252255 (C4 (Web Text))

Max Activating Token Index: 254

Text #17

Max Range: 0.3189. Min Range: -0.3189

Max Act: 0.0756. Min Act: -0.0000

Data Index: 939828 (C4 (Web Text))

Max Activating Token Index: 886

Text #18

Max Range: 0.3189. Min Range: -0.3189

Max Act: 0.0680. Min Act: -0.0001

Data Index: 1188233 (C4 (Web Text))

Max Activating Token Index: 353

Text #19

Max Range: 0.3189. Min Range: -0.3189

Max Act: 0.0744. Min Act: -0.0001

Data Index: 1277403 (C4 (Web Text))

Max Activating Token Index: 293