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

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

Neuron 5161 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.6757. Min Range: -1.6757

Max Act: 1.6757. Min Act: -0.0000

Data Index: 1119580 (C4 (Web Text))

Max Activating Token Index: 652

Text #1

Max Range: 1.6757. Min Range: -1.6757

Max Act: 1.6515. Min Act: -0.0000

Data Index: 1074301 (C4 (Web Text))

Max Activating Token Index: 702

Text #2

Max Range: 1.6757. Min Range: -1.6757

Max Act: 1.5530. Min Act: -0.0000

Data Index: 697692 (C4 (Web Text))

Max Activating Token Index: 829

Text #3

Max Range: 1.6757. Min Range: -1.6757

Max Act: 1.6425. Min Act: -0.0000

Data Index: 207939 (C4 (Web Text))

Max Activating Token Index: 660

Text #4

Max Range: 1.6757. Min Range: -1.6757

Max Act: 1.5741. Min Act: -0.0000

Data Index: 594609 (C4 (Web Text))

Max Activating Token Index: 703

Text #5

Max Range: 1.6757. Min Range: -1.6757

Max Act: 1.6657. Min Act: -0.0000

Data Index: 197599 (C4 (Web Text))

Max Activating Token Index: 491

Text #6

Max Range: 1.6757. Min Range: -1.6757

Max Act: 1.4743. Min Act: -0.0000

Data Index: 1220100 (C4 (Web Text))

Max Activating Token Index: 550

Text #7

Max Range: 1.6757. Min Range: -1.6757

Max Act: 1.4683. Min Act: -0.0000

Data Index: 362257 (C4 (Web Text))

Max Activating Token Index: 519

Text #8

Max Range: 1.6757. Min Range: -1.6757

Max Act: 1.5569. Min Act: -0.0000

Data Index: 12147 (C4 (Web Text))

Max Activating Token Index: 934

Text #9

Max Range: 1.6757. Min Range: -1.6757

Max Act: 1.4655. Min Act: -0.0000

Data Index: 551913 (C4 (Web Text))

Max Activating Token Index: 419

Text #10

Max Range: 1.6757. Min Range: -1.6757

Max Act: 1.5598. Min Act: -0.0000

Data Index: 71790 (C4 (Web Text))

Max Activating Token Index: 424

Text #11

Max Range: 1.6757. Min Range: -1.6757

Max Act: 1.3788. Min Act: -0.0000

Data Index: 200755 (C4 (Web Text))

Max Activating Token Index: 737

Text #12

Max Range: 1.6757. Min Range: -1.6757

Max Act: 1.5372. Min Act: -0.0000

Data Index: 1338311 (C4 (Web Text))

Max Activating Token Index: 194

Text #13

Max Range: 1.6757. Min Range: -1.6757

Max Act: 1.4946. Min Act: -0.0000

Data Index: 23568 (C4 (Web Text))

Max Activating Token Index: 801

Text #14

Max Range: 1.6757. Min Range: -1.6757

Max Act: 1.5812. Min Act: -0.0000

Data Index: 423177 (C4 (Web Text))

Max Activating Token Index: 769

Text #15

Max Range: 1.6757. Min Range: -1.6757

Max Act: 1.5739. Min Act: -0.0000

Data Index: 1331761 (C4 (Web Text))

Max Activating Token Index: 722

Text #16

Max Range: 1.6757. Min Range: -1.6757

Max Act: 1.3903. Min Act: -0.0000

Data Index: 81562 (C4 (Web Text))

Max Activating Token Index: 431

Text #17

Max Range: 1.6757. Min Range: -1.6757

Max Act: 1.3827. Min Act: -0.0000

Data Index: 662385 (C4 (Web Text))

Max Activating Token Index: 94

Text #18

Max Range: 1.6757. Min Range: -1.6757

Max Act: 1.5623. Min Act: -0.0000

Data Index: 363657 (C4 (Web Text))

Max Activating Token Index: 210

Text #19

Max Range: 1.6757. Min Range: -1.6757

Max Act: 1.4664. Min Act: -0.0000

Data Index: 1161277 (C4 (Web Text))

Max Activating Token Index: 222