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

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

Neuron 1298 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: 1.2897. Min Range: -1.2897

Max Act: 1.2602. Min Act: -0.0001

Data Index: 449591 (C4 (Web Text))

Max Activating Token Index: 662

Text #1

Max Range: 1.2897. Min Range: -1.2897

Max Act: 1.2807. Min Act: -0.0001

Data Index: 1332528 (C4 (Web Text))

Max Activating Token Index: 718

Text #2

Max Range: 1.2897. Min Range: -1.2897

Max Act: 1.2897. Min Act: -0.0001

Data Index: 938665 (C4 (Web Text))

Max Activating Token Index: 391

Text #3

Max Range: 1.2897. Min Range: -1.2897

Max Act: 1.2594. Min Act: -0.0001

Data Index: 99567 (C4 (Web Text))

Max Activating Token Index: 262

Text #4

Max Range: 1.2897. Min Range: -1.2897

Max Act: 1.1684. Min Act: -0.0001

Data Index: 885590 (C4 (Web Text))

Max Activating Token Index: 131

Text #5

Max Range: 1.2897. Min Range: -1.2897

Max Act: 1.1164. Min Act: -0.0001

Data Index: 461037 (C4 (Web Text))

Max Activating Token Index: 555

Text #6

Max Range: 1.2897. Min Range: -1.2897

Max Act: 1.0688. Min Act: -0.0001

Data Index: 233832 (C4 (Web Text))

Max Activating Token Index: 633

Text #7

Max Range: 1.2897. Min Range: -1.2897

Max Act: 1.0879. Min Act: -0.0001

Data Index: 1201966 (C4 (Web Text))

Max Activating Token Index: 773

Text #8

Max Range: 1.2897. Min Range: -1.2897

Max Act: 1.0725. Min Act: -0.0001

Data Index: 495057 (C4 (Web Text))

Max Activating Token Index: 432

Text #9

Max Range: 1.2897. Min Range: -1.2897

Max Act: 1.0378. Min Act: -0.0001

Data Index: 799765 (C4 (Web Text))

Max Activating Token Index: 613

Text #10

Max Range: 1.2897. Min Range: -1.2897

Max Act: 0.9822. Min Act: -0.0001

Data Index: 553779 (C4 (Web Text))

Max Activating Token Index: 441

Text #11

Max Range: 1.2897. Min Range: -1.2897

Max Act: 0.8757. Min Act: -0.0001

Data Index: 1142605 (C4 (Web Text))

Max Activating Token Index: 677

Text #12

Max Range: 1.2897. Min Range: -1.2897

Max Act: 1.0337. Min Act: -0.0001

Data Index: 953296 (C4 (Web Text))

Max Activating Token Index: 628

Text #13

Max Range: 1.2897. Min Range: -1.2897

Max Act: 0.8294. Min Act: -0.0001

Data Index: 860611 (C4 (Web Text))

Max Activating Token Index: 568

Text #14

Max Range: 1.2897. Min Range: -1.2897

Max Act: 0.8806. Min Act: -0.0001

Data Index: 1315811 (C4 (Web Text))

Max Activating Token Index: 538

Text #15

Max Range: 1.2897. Min Range: -1.2897

Max Act: 0.7780. Min Act: -0.0001

Data Index: 350880 (C4 (Web Text))

Max Activating Token Index: 244

Text #16

Max Range: 1.2897. Min Range: -1.2897

Max Act: 0.8645. Min Act: -0.0001

Data Index: 407109 (C4 (Web Text))

Max Activating Token Index: 117

Text #17

Max Range: 1.2897. Min Range: -1.2897

Max Act: 0.9334. Min Act: -0.0001

Data Index: 1128886 (C4 (Web Text))

Max Activating Token Index: 481

Text #18

Max Range: 1.2897. Min Range: -1.2897

Max Act: 0.8650. Min Act: -0.0001

Data Index: 437380 (C4 (Web Text))

Max Activating Token Index: 768

Text #19

Max Range: 1.2897. Min Range: -1.2897

Max Act: 0.7804. Min Act: -0.0001

Data Index: 1203448 (C4 (Web Text))

Max Activating Token Index: 336