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

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

Neuron 1426 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 1.1100. Min Range: -1.1100

Max Act: 1.1100. Min Act: -0.0001

Data Index: 899823 (C4 (Web Text))

Max Activating Token Index: 185

Text #1

Max Range: 1.1100. Min Range: -1.1100

Max Act: 0.9939. Min Act: -0.0001

Data Index: 13800 (C4 (Web Text))

Max Activating Token Index: 915

Text #2

Max Range: 1.1100. Min Range: -1.1100

Max Act: 1.0254. Min Act: -0.0001

Data Index: 341796 (C4 (Web Text))

Max Activating Token Index: 855

Text #3

Max Range: 1.1100. Min Range: -1.1100

Max Act: 0.9832. Min Act: -0.0001

Data Index: 1085332 (C4 (Web Text))

Max Activating Token Index: 860

Text #4

Max Range: 1.1100. Min Range: -1.1100

Max Act: 1.0446. Min Act: -0.0001

Data Index: 1246490 (C4 (Web Text))

Max Activating Token Index: 164

Text #5

Max Range: 1.1100. Min Range: -1.1100

Max Act: 1.0340. Min Act: -0.0001

Data Index: 910732 (C4 (Web Text))

Max Activating Token Index: 626

Text #6

Max Range: 1.1100. Min Range: -1.1100

Max Act: 0.9974. Min Act: -0.0001

Data Index: 1095674 (C4 (Web Text))

Max Activating Token Index: 891

Text #7

Max Range: 1.1100. Min Range: -1.1100

Max Act: 0.9906. Min Act: -0.0001

Data Index: 320097 (C4 (Web Text))

Max Activating Token Index: 614

Text #8

Max Range: 1.1100. Min Range: -1.1100

Max Act: 0.9580. Min Act: -0.0001

Data Index: 1303633 (C4 (Web Text))

Max Activating Token Index: 822

Text #9

Max Range: 1.1100. Min Range: -1.1100

Max Act: 0.9404. Min Act: -0.0001

Data Index: 795062 (C4 (Web Text))

Max Activating Token Index: 80

Text #10

Max Range: 1.1100. Min Range: -1.1100

Max Act: 0.8398. Min Act: -0.0001

Data Index: 578606 (C4 (Web Text))

Max Activating Token Index: 61

Text #11

Max Range: 1.1100. Min Range: -1.1100

Max Act: 0.9574. Min Act: -0.0001

Data Index: 507877 (C4 (Web Text))

Max Activating Token Index: 167

Text #12

Max Range: 1.1100. Min Range: -1.1100

Max Act: 0.9145. Min Act: -0.0001

Data Index: 1217130 (C4 (Web Text))

Max Activating Token Index: 522

Text #13

Max Range: 1.1100. Min Range: -1.1100

Max Act: 0.9387. Min Act: -0.0001

Data Index: 515409 (C4 (Web Text))

Max Activating Token Index: 237

Text #14

Max Range: 1.1100. Min Range: -1.1100

Max Act: 0.8883. Min Act: -0.0001

Data Index: 981317 (C4 (Web Text))

Max Activating Token Index: 777

Text #15

Max Range: 1.1100. Min Range: -1.1100

Max Act: 0.8793. Min Act: -0.0001

Data Index: 385554 (C4 (Web Text))

Max Activating Token Index: 76

Text #16

Max Range: 1.1100. Min Range: -1.1100

Max Act: 0.8471. Min Act: -0.0001

Data Index: 276191 (C4 (Web Text))

Max Activating Token Index: 498

Text #17

Max Range: 1.1100. Min Range: -1.1100

Max Act: 0.8989. Min Act: -0.0001

Data Index: 739562 (C4 (Web Text))

Max Activating Token Index: 986

Text #18

Max Range: 1.1100. Min Range: -1.1100

Max Act: 0.8963. Min Act: -0.0001

Data Index: 383208 (C4 (Web Text))

Max Activating Token Index: 1023

Text #19

Max Range: 1.1100. Min Range: -1.1100

Max Act: 0.8884. Min Act: -0.0001

Data Index: 537105 (C4 (Web Text))

Max Activating Token Index: 213