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

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

Neuron 5435 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: 2.1041. Min Range: -2.1041

Max Act: 2.0445. Min Act: -0.0000

Data Index: 623530 (C4 (Web Text))

Max Activating Token Index: 797

Text #1

Max Range: 2.1041. Min Range: -2.1041

Max Act: 2.1041. Min Act: -0.0000

Data Index: 632788 (C4 (Web Text))

Max Activating Token Index: 812

Text #2

Max Range: 2.1041. Min Range: -2.1041

Max Act: 2.0816. Min Act: -0.0000

Data Index: 297548 (C4 (Web Text))

Max Activating Token Index: 505

Text #3

Max Range: 2.1041. Min Range: -2.1041

Max Act: 2.0650. Min Act: -0.0000

Data Index: 132935 (C4 (Web Text))

Max Activating Token Index: 500

Text #4

Max Range: 2.1041. Min Range: -2.1041

Max Act: 2.0458. Min Act: -0.0000

Data Index: 487665 (C4 (Web Text))

Max Activating Token Index: 466

Text #5

Max Range: 2.1041. Min Range: -2.1041

Max Act: 1.8911. Min Act: -0.0000

Data Index: 1090864 (C4 (Web Text))

Max Activating Token Index: 882

Text #6

Max Range: 2.1041. Min Range: -2.1041

Max Act: 2.0161. Min Act: -0.0000

Data Index: 534253 (C4 (Web Text))

Max Activating Token Index: 74

Text #7

Max Range: 2.1041. Min Range: -2.1041

Max Act: 1.9939. Min Act: 0.0000

Data Index: 1288104 (C4 (Web Text))

Max Activating Token Index: 616

Text #8

Max Range: 2.1041. Min Range: -2.1041

Max Act: 1.8351. Min Act: -0.0000

Data Index: 1358839 (C4 (Web Text))

Max Activating Token Index: 656

Text #9

Max Range: 2.1041. Min Range: -2.1041

Max Act: 1.7978. Min Act: 0.0001

Data Index: 694722 (C4 (Web Text))

Max Activating Token Index: 127

Text #10

Max Range: 2.1041. Min Range: -2.1041

Max Act: 1.8567. Min Act: -0.0000

Data Index: 1251977 (C4 (Web Text))

Max Activating Token Index: 362

Text #11

Max Range: 2.1041. Min Range: -2.1041

Max Act: 1.8403. Min Act: 0.0000

Data Index: 94346 (C4 (Web Text))

Max Activating Token Index: 1021

Text #12

Max Range: 2.1041. Min Range: -2.1041

Max Act: 1.8553. Min Act: -0.0000

Data Index: 1312313 (C4 (Web Text))

Max Activating Token Index: 716

Text #13

Max Range: 2.1041. Min Range: -2.1041

Max Act: 1.9547. Min Act: 0.0000

Data Index: 304360 (C4 (Web Text))

Max Activating Token Index: 805

Text #14

Max Range: 2.1041. Min Range: -2.1041

Max Act: 1.8414. Min Act: -0.0000

Data Index: 1225412 (C4 (Web Text))

Max Activating Token Index: 839

Text #15

Max Range: 2.1041. Min Range: -2.1041

Max Act: 1.7377. Min Act: -0.0000

Data Index: 251571 (C4 (Web Text))

Max Activating Token Index: 29

Text #16

Max Range: 2.1041. Min Range: -2.1041

Max Act: 1.8285. Min Act: -0.0000

Data Index: 414751 (C4 (Web Text))

Max Activating Token Index: 268

Text #17

Max Range: 2.1041. Min Range: -2.1041

Max Act: 1.8106. Min Act: -0.0000

Data Index: 490126 (C4 (Web Text))

Max Activating Token Index: 979

Text #18

Max Range: 2.1041. Min Range: -2.1041

Max Act: 1.7100. Min Act: 0.0000

Data Index: 82957 (C4 (Web Text))

Max Activating Token Index: 829

Text #19

Max Range: 2.1041. Min Range: -2.1041

Max Act: 1.7076. Min Act: -0.0000

Data Index: 1209730 (C4 (Web Text))

Max Activating Token Index: 286