Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 3055 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.6761. Min Range: -0.6761

Max Act: 0.6664. Min Act: -0.0001

Data Index: 1003985 (C4 (Web Text))

Max Activating Token Index: 1000

Text #1

Max Range: 0.6761. Min Range: -0.6761

Max Act: 0.6761. Min Act: -0.0001

Data Index: 443046 (C4 (Web Text))

Max Activating Token Index: 658

Text #2

Max Range: 0.6761. Min Range: -0.6761

Max Act: 0.6400. Min Act: -0.0001

Data Index: 511384 (C4 (Web Text))

Max Activating Token Index: 241

Text #3

Max Range: 0.6761. Min Range: -0.6761

Max Act: 0.6016. Min Act: -0.0001

Data Index: 883764 (C4 (Web Text))

Max Activating Token Index: 117

Text #4

Max Range: 0.6761. Min Range: -0.6761

Max Act: 0.5877. Min Act: -0.0001

Data Index: 1173530 (C4 (Web Text))

Max Activating Token Index: 777

Text #5

Max Range: 0.6761. Min Range: -0.6761

Max Act: 0.5857. Min Act: -0.0001

Data Index: 373358 (C4 (Web Text))

Max Activating Token Index: 65

Text #6

Max Range: 0.6761. Min Range: -0.6761

Max Act: 0.5717. Min Act: -0.0001

Data Index: 655048 (C4 (Web Text))

Max Activating Token Index: 635

Text #7

Max Range: 0.6761. Min Range: -0.6761

Max Act: 0.5341. Min Act: -0.0001

Data Index: 1257170 (C4 (Web Text))

Max Activating Token Index: 310

Text #8

Max Range: 0.6761. Min Range: -0.6761

Max Act: 0.6193. Min Act: -0.0001

Data Index: 1083424 (C4 (Web Text))

Max Activating Token Index: 385

Text #9

Max Range: 0.6761. Min Range: -0.6761

Max Act: 0.5945. Min Act: -0.0001

Data Index: 55842 (C4 (Web Text))

Max Activating Token Index: 963

Text #10

Max Range: 0.6761. Min Range: -0.6761

Max Act: 0.6010. Min Act: -0.0001

Data Index: 1195899 (C4 (Web Text))

Max Activating Token Index: 322

Text #11

Max Range: 0.6761. Min Range: -0.6761

Max Act: 0.5164. Min Act: -0.0001

Data Index: 134062 (C4 (Web Text))

Max Activating Token Index: 533

Text #12

Max Range: 0.6761. Min Range: -0.6761

Max Act: 0.5721. Min Act: -0.0001

Data Index: 111857 (C4 (Web Text))

Max Activating Token Index: 803

Text #13

Max Range: 0.6761. Min Range: -0.6761

Max Act: 0.5540. Min Act: -0.0001

Data Index: 861937 (C4 (Web Text))

Max Activating Token Index: 597

Text #14

Max Range: 0.6761. Min Range: -0.6761

Max Act: 0.5289. Min Act: -0.0001

Data Index: 376100 (C4 (Web Text))

Max Activating Token Index: 877

Text #15

Max Range: 0.6761. Min Range: -0.6761

Max Act: 0.6050. Min Act: -0.0001

Data Index: 463301 (C4 (Web Text))

Max Activating Token Index: 549

Text #16

Max Range: 0.6761. Min Range: -0.6761

Max Act: 0.5869. Min Act: -0.0001

Data Index: 1273428 (C4 (Web Text))

Max Activating Token Index: 743

Text #17

Max Range: 0.6761. Min Range: -0.6761

Max Act: 0.5083. Min Act: -0.0001

Data Index: 518000 (C4 (Web Text))

Max Activating Token Index: 301

Text #18

Max Range: 0.6761. Min Range: -0.6761

Max Act: 0.5635. Min Act: -0.0001

Data Index: 685899 (C4 (Web Text))

Max Activating Token Index: 122

Text #19

Max Range: 0.6761. Min Range: -0.6761

Max Act: 0.4883. Min Act: -0.0001

Data Index: 456017 (C4 (Web Text))

Max Activating Token Index: 360