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

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

Neuron 1490 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 7.0651. Min Range: -7.0651

Max Act: 7.0010. Min Act: -0.0000

Data Index: 1147590 (C4 (Web Text))

Max Activating Token Index: 770

Text #1

Max Range: 7.0651. Min Range: -7.0651

Max Act: 7.0651. Min Act: -0.0000

Data Index: 1185151 (C4 (Web Text))

Max Activating Token Index: 316

Text #2

Max Range: 7.0651. Min Range: -7.0651

Max Act: 6.0233. Min Act: -0.0000

Data Index: 505679 (C4 (Web Text))

Max Activating Token Index: 499

Text #3

Max Range: 7.0651. Min Range: -7.0651

Max Act: 5.5838. Min Act: -0.0000

Data Index: 130101 (C4 (Web Text))

Max Activating Token Index: 965

Text #4

Max Range: 7.0651. Min Range: -7.0651

Max Act: 5.5150. Min Act: -0.0000

Data Index: 166307 (C4 (Web Text))

Max Activating Token Index: 662

Text #5

Max Range: 7.0651. Min Range: -7.0651

Max Act: 5.6753. Min Act: -0.0000

Data Index: 1275559 (C4 (Web Text))

Max Activating Token Index: 323

Text #6

Max Range: 7.0651. Min Range: -7.0651

Max Act: 5.3837. Min Act: -0.0000

Data Index: 239137 (C4 (Web Text))

Max Activating Token Index: 316

Text #7

Max Range: 7.0651. Min Range: -7.0651

Max Act: 4.9843. Min Act: -0.0000

Data Index: 31582 (C4 (Web Text))

Max Activating Token Index: 876

Text #8

Max Range: 7.0651. Min Range: -7.0651

Max Act: 4.9906. Min Act: -0.0000

Data Index: 324357 (C4 (Web Text))

Max Activating Token Index: 75

Text #9

Max Range: 7.0651. Min Range: -7.0651

Max Act: 4.9012. Min Act: -0.0000

Data Index: 1195830 (C4 (Web Text))

Max Activating Token Index: 685

Text #10

Max Range: 7.0651. Min Range: -7.0651

Max Act: 4.8927. Min Act: -0.0000

Data Index: 1303901 (C4 (Web Text))

Max Activating Token Index: 469

Text #11

Max Range: 7.0651. Min Range: -7.0651

Max Act: 4.8453. Min Act: -0.0000

Data Index: 57189 (C4 (Web Text))

Max Activating Token Index: 17

Text #12

Max Range: 7.0651. Min Range: -7.0651

Max Act: 5.0798. Min Act: -0.0000

Data Index: 850806 (C4 (Web Text))

Max Activating Token Index: 305

Text #13

Max Range: 7.0651. Min Range: -7.0651

Max Act: 4.7282. Min Act: -0.0000

Data Index: 855077 (C4 (Web Text))

Max Activating Token Index: 987

Text #14

Max Range: 7.0651. Min Range: -7.0651

Max Act: 5.0036. Min Act: -0.0000

Data Index: 387986 (C4 (Web Text))

Max Activating Token Index: 849

Text #15

Max Range: 7.0651. Min Range: -7.0651

Max Act: 4.9619. Min Act: -0.0000

Data Index: 993640 (C4 (Web Text))

Max Activating Token Index: 915

Text #16

Max Range: 7.0651. Min Range: -7.0651

Max Act: 4.8152. Min Act: -0.0000

Data Index: 895274 (C4 (Web Text))

Max Activating Token Index: 888

Text #17

Max Range: 7.0651. Min Range: -7.0651

Max Act: 4.7497. Min Act: -0.0000

Data Index: 448420 (C4 (Web Text))

Max Activating Token Index: 595

Text #18

Max Range: 7.0651. Min Range: -7.0651

Max Act: 4.6573. Min Act: -0.0000

Data Index: 814165 (C4 (Web Text))

Max Activating Token Index: 759

Text #19

Max Range: 7.0651. Min Range: -7.0651

Max Act: 4.5588. Min Act: -0.0000

Data Index: 609540 (C4 (Web Text))

Max Activating Token Index: 758