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

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

Neuron 3050 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: 0.1063. Min Range: -0.1063

Max Act: 0.0939. Min Act: -0.0001

Data Index: 549600 (C4 (Web Text))

Max Activating Token Index: 285

Text #1

Max Range: 0.1063. Min Range: -0.1063

Max Act: 0.1041. Min Act: -0.0001

Data Index: 945315 (C4 (Web Text))

Max Activating Token Index: 165

Text #2

Max Range: 0.1063. Min Range: -0.1063

Max Act: 0.1038. Min Act: -0.0001

Data Index: 569869 (C4 (Web Text))

Max Activating Token Index: 769

Text #3

Max Range: 0.1063. Min Range: -0.1063

Max Act: 0.1008. Min Act: -0.0001

Data Index: 490649 (C4 (Web Text))

Max Activating Token Index: 944

Text #4

Max Range: 0.1063. Min Range: -0.1063

Max Act: 0.1007. Min Act: -0.0001

Data Index: 96273 (C4 (Web Text))

Max Activating Token Index: 87

Text #5

Max Range: 0.1063. Min Range: -0.1063

Max Act: 0.1063. Min Act: -0.0001

Data Index: 1187652 (C4 (Web Text))

Max Activating Token Index: 524

Text #6

Max Range: 0.1063. Min Range: -0.1063

Max Act: 0.0948. Min Act: -0.0001

Data Index: 141473 (C4 (Web Text))

Max Activating Token Index: 915

Text #7

Max Range: 0.1063. Min Range: -0.1063

Max Act: 0.0932. Min Act: -0.0001

Data Index: 83749 (C4 (Web Text))

Max Activating Token Index: 485

Text #8

Max Range: 0.1063. Min Range: -0.1063

Max Act: 0.0905. Min Act: -0.0001

Data Index: 1154020 (C4 (Web Text))

Max Activating Token Index: 213

Text #9

Max Range: 0.1063. Min Range: -0.1063

Max Act: 0.0887. Min Act: -0.0001

Data Index: 79570 (C4 (Web Text))

Max Activating Token Index: 201

Text #10

Max Range: 0.1063. Min Range: -0.1063

Max Act: 0.0919. Min Act: -0.0001

Data Index: 347392 (C4 (Web Text))

Max Activating Token Index: 308

Text #11

Max Range: 0.1063. Min Range: -0.1063

Max Act: 0.0881. Min Act: -0.0001

Data Index: 531073 (C4 (Web Text))

Max Activating Token Index: 262

Text #12

Max Range: 0.1063. Min Range: -0.1063

Max Act: 0.0948. Min Act: -0.0001

Data Index: 706566 (C4 (Web Text))

Max Activating Token Index: 813

Text #13

Max Range: 0.1063. Min Range: -0.1063

Max Act: 0.0912. Min Act: -0.0001

Data Index: 1239824 (C4 (Web Text))

Max Activating Token Index: 858

Text #14

Max Range: 0.1063. Min Range: -0.1063

Max Act: 0.0937. Min Act: -0.0001

Data Index: 567616 (C4 (Web Text))

Max Activating Token Index: 131

Text #15

Max Range: 0.1063. Min Range: -0.1063

Max Act: 0.0897. Min Act: -0.0001

Data Index: 659071 (C4 (Web Text))

Max Activating Token Index: 339

Text #16

Max Range: 0.1063. Min Range: -0.1063

Max Act: 0.0960. Min Act: -0.0001

Data Index: 25674 (C4 (Web Text))

Max Activating Token Index: 501

Text #17

Max Range: 0.1063. Min Range: -0.1063

Max Act: 0.0910. Min Act: -0.0001

Data Index: 968914 (C4 (Web Text))

Max Activating Token Index: 607

Text #18

Max Range: 0.1063. Min Range: -0.1063

Max Act: 0.0927. Min Act: -0.0001

Data Index: 500858 (C4 (Web Text))

Max Activating Token Index: 620

Text #19

Max Range: 0.1063. Min Range: -0.1063

Max Act: 0.0888. Min Act: -0.0001

Data Index: 449743 (C4 (Web Text))

Max Activating Token Index: 468