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

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

Neuron 4553 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.0939. Min Range: -5.0939

Max Act: 5.0939. Min Act: -0.0000

Data Index: 398076 (C4 (Web Text))

Max Activating Token Index: 598

Text #1

Max Range: 5.0939. Min Range: -5.0939

Max Act: 4.9991. Min Act: -0.0000

Data Index: 840790 (C4 (Web Text))

Max Activating Token Index: 533

Text #2

Max Range: 5.0939. Min Range: -5.0939

Max Act: 4.9212. Min Act: -0.0000

Data Index: 794087 (C4 (Web Text))

Max Activating Token Index: 570

Text #3

Max Range: 5.0939. Min Range: -5.0939

Max Act: 4.8872. Min Act: -0.0000

Data Index: 748018 (C4 (Web Text))

Max Activating Token Index: 759

Text #4

Max Range: 5.0939. Min Range: -5.0939

Max Act: 4.7668. Min Act: -0.0000

Data Index: 250913 (C4 (Web Text))

Max Activating Token Index: 98

Text #5

Max Range: 5.0939. Min Range: -5.0939

Max Act: 4.5940. Min Act: -0.0000

Data Index: 892272 (C4 (Web Text))

Max Activating Token Index: 559

Text #6

Max Range: 5.0939. Min Range: -5.0939

Max Act: 4.2646. Min Act: -0.0000

Data Index: 1229035 (C4 (Web Text))

Max Activating Token Index: 767

Text #7

Max Range: 5.0939. Min Range: -5.0939

Max Act: 4.5526. Min Act: -0.0000

Data Index: 130264 (C4 (Web Text))

Max Activating Token Index: 268

Text #8

Max Range: 5.0939. Min Range: -5.0939

Max Act: 4.1958. Min Act: -0.0000

Data Index: 1246140 (C4 (Web Text))

Max Activating Token Index: 166

Text #9

Max Range: 5.0939. Min Range: -5.0939

Max Act: 4.3013. Min Act: -0.0000

Data Index: 1276871 (C4 (Web Text))

Max Activating Token Index: 680

Text #10

Max Range: 5.0939. Min Range: -5.0939

Max Act: 4.2681. Min Act: -0.0000

Data Index: 917755 (C4 (Web Text))

Max Activating Token Index: 642

Text #11

Max Range: 5.0939. Min Range: -5.0939

Max Act: 4.2469. Min Act: -0.0000

Data Index: 903842 (C4 (Web Text))

Max Activating Token Index: 676

Text #12

Max Range: 5.0939. Min Range: -5.0939

Max Act: 3.8602. Min Act: -0.0000

Data Index: 342679 (C4 (Web Text))

Max Activating Token Index: 939

Text #13

Max Range: 5.0939. Min Range: -5.0939

Max Act: 4.0500. Min Act: -0.0000

Data Index: 218776 (C4 (Web Text))

Max Activating Token Index: 648

Text #14

Max Range: 5.0939. Min Range: -5.0939

Max Act: 4.0010. Min Act: -0.0000

Data Index: 1183676 (C4 (Web Text))

Max Activating Token Index: 767

Text #15

Max Range: 5.0939. Min Range: -5.0939

Max Act: 3.5733. Min Act: -0.0000

Data Index: 589915 (C4 (Web Text))

Max Activating Token Index: 944

Text #16

Max Range: 5.0939. Min Range: -5.0939

Max Act: 3.7336. Min Act: -0.0000

Data Index: 1063327 (C4 (Web Text))

Max Activating Token Index: 986

Text #17

Max Range: 5.0939. Min Range: -5.0939

Max Act: 3.9260. Min Act: -0.0000

Data Index: 22691 (C4 (Web Text))

Max Activating Token Index: 255

Text #18

Max Range: 5.0939. Min Range: -5.0939

Max Act: 3.7272. Min Act: -0.0000

Data Index: 1085733 (C4 (Web Text))

Max Activating Token Index: 885

Text #19

Max Range: 5.0939. Min Range: -5.0939

Max Act: 3.7117. Min Act: -0.0000

Data Index: 1226282 (C4 (Web Text))

Max Activating Token Index: 291