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

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

Neuron 3978 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2949. Min Range: -0.2949

Max Act: 0.2949. Min Act: -0.0000

Data Index: 797844 (C4 (Web Text))

Max Activating Token Index: 754

Text #1

Max Range: 0.2949. Min Range: -0.2949

Max Act: 0.2842. Min Act: -0.0000

Data Index: 398718 (C4 (Web Text))

Max Activating Token Index: 129

Text #2

Max Range: 0.2949. Min Range: -0.2949

Max Act: 0.2763. Min Act: -0.0000

Data Index: 1042101 (C4 (Web Text))

Max Activating Token Index: 151

Text #3

Max Range: 0.2949. Min Range: -0.2949

Max Act: 0.2798. Min Act: -0.0000

Data Index: 552570 (C4 (Web Text))

Max Activating Token Index: 645

Text #4

Max Range: 0.2949. Min Range: -0.2949

Max Act: 0.2730. Min Act: -0.0000

Data Index: 1261537 (C4 (Web Text))

Max Activating Token Index: 961

Text #5

Max Range: 0.2949. Min Range: -0.2949

Max Act: 0.2614. Min Act: -0.0000

Data Index: 1305218 (C4 (Web Text))

Max Activating Token Index: 463

Text #6

Max Range: 0.2949. Min Range: -0.2949

Max Act: 0.2676. Min Act: -0.0000

Data Index: 986842 (C4 (Web Text))

Max Activating Token Index: 690

Text #7

Max Range: 0.2949. Min Range: -0.2949

Max Act: 0.2565. Min Act: -0.0000

Data Index: 9310 (C4 (Web Text))

Max Activating Token Index: 99

Text #8

Max Range: 0.2949. Min Range: -0.2949

Max Act: 0.2674. Min Act: -0.0001

Data Index: 67985 (C4 (Web Text))

Max Activating Token Index: 127

Text #9

Max Range: 0.2949. Min Range: -0.2949

Max Act: 0.2636. Min Act: -0.0000

Data Index: 1033433 (C4 (Web Text))

Max Activating Token Index: 154

Text #10

Max Range: 0.2949. Min Range: -0.2949

Max Act: 0.2447. Min Act: -0.0000

Data Index: 12565 (C4 (Web Text))

Max Activating Token Index: 910

Text #11

Max Range: 0.2949. Min Range: -0.2949

Max Act: 0.2610. Min Act: -0.0000

Data Index: 696013 (C4 (Web Text))

Max Activating Token Index: 666

Text #12

Max Range: 0.2949. Min Range: -0.2949

Max Act: 0.2515. Min Act: -0.0000

Data Index: 630809 (C4 (Web Text))

Max Activating Token Index: 1009

Text #13

Max Range: 0.2949. Min Range: -0.2949

Max Act: 0.2517. Min Act: -0.0000

Data Index: 1207112 (C4 (Web Text))

Max Activating Token Index: 396

Text #14

Max Range: 0.2949. Min Range: -0.2949

Max Act: 0.2570. Min Act: -0.0000

Data Index: 671957 (C4 (Web Text))

Max Activating Token Index: 103

Text #15

Max Range: 0.2949. Min Range: -0.2949

Max Act: 0.2549. Min Act: -0.0000

Data Index: 751967 (C4 (Web Text))

Max Activating Token Index: 396

Text #16

Max Range: 0.2949. Min Range: -0.2949

Max Act: 0.2373. Min Act: -0.0000

Data Index: 970124 (C4 (Web Text))

Max Activating Token Index: 393

Text #17

Max Range: 0.2949. Min Range: -0.2949

Max Act: 0.2503. Min Act: -0.0000

Data Index: 989897 (C4 (Web Text))

Max Activating Token Index: 797

Text #18

Max Range: 0.2949. Min Range: -0.2949

Max Act: 0.2410. Min Act: -0.0000

Data Index: 794792 (C4 (Web Text))

Max Activating Token Index: 411

Text #19

Max Range: 0.2949. Min Range: -0.2949

Max Act: 0.2491. Min Act: -0.0000

Data Index: 41045 (C4 (Web Text))

Max Activating Token Index: 943