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

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

Neuron 6074 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.8948. Min Range: -1.8948

Max Act: 1.8948. Min Act: -0.0000

Data Index: 1238100 (C4 (Web Text))

Max Activating Token Index: 623

Text #1

Max Range: 1.8948. Min Range: -1.8948

Max Act: 1.8468. Min Act: -0.0000

Data Index: 386120 (C4 (Web Text))

Max Activating Token Index: 718

Text #2

Max Range: 1.8948. Min Range: -1.8948

Max Act: 1.7720. Min Act: -0.0000

Data Index: 985693 (C4 (Web Text))

Max Activating Token Index: 642

Text #3

Max Range: 1.8948. Min Range: -1.8948

Max Act: 1.7369. Min Act: -0.0000

Data Index: 1173148 (C4 (Web Text))

Max Activating Token Index: 331

Text #4

Max Range: 1.8948. Min Range: -1.8948

Max Act: 1.7546. Min Act: -0.0000

Data Index: 1111464 (C4 (Web Text))

Max Activating Token Index: 127

Text #5

Max Range: 1.8948. Min Range: -1.8948

Max Act: 1.6016. Min Act: -0.0000

Data Index: 188296 (C4 (Web Text))

Max Activating Token Index: 581

Text #6

Max Range: 1.8948. Min Range: -1.8948

Max Act: 1.4416. Min Act: -0.0000

Data Index: 29719 (C4 (Web Text))

Max Activating Token Index: 632

Text #7

Max Range: 1.8948. Min Range: -1.8948

Max Act: 1.4966. Min Act: -0.0000

Data Index: 1201306 (C4 (Web Text))

Max Activating Token Index: 774

Text #8

Max Range: 1.8948. Min Range: -1.8948

Max Act: 1.5369. Min Act: -0.0000

Data Index: 391350 (C4 (Web Text))

Max Activating Token Index: 235

Text #9

Max Range: 1.8948. Min Range: -1.8948

Max Act: 1.3856. Min Act: -0.0000

Data Index: 745834 (C4 (Web Text))

Max Activating Token Index: 407

Text #10

Max Range: 1.8948. Min Range: -1.8948

Max Act: 1.3713. Min Act: -0.0000

Data Index: 1314688 (C4 (Web Text))

Max Activating Token Index: 443

Text #11

Max Range: 1.8948. Min Range: -1.8948

Max Act: 1.3617. Min Act: -0.0000

Data Index: 1047431 (C4 (Web Text))

Max Activating Token Index: 425

Text #12

Max Range: 1.8948. Min Range: -1.8948

Max Act: 1.3353. Min Act: -0.0000

Data Index: 543143 (C4 (Web Text))

Max Activating Token Index: 88

Text #13

Max Range: 1.8948. Min Range: -1.8948

Max Act: 1.3285. Min Act: 0.0000

Data Index: 755503 (C4 (Web Text))

Max Activating Token Index: 394

Text #14

Max Range: 1.8948. Min Range: -1.8948

Max Act: 1.3109. Min Act: -0.0000

Data Index: 826540 (C4 (Web Text))

Max Activating Token Index: 234

Text #15

Max Range: 1.8948. Min Range: -1.8948

Max Act: 1.3876. Min Act: -0.0000

Data Index: 1167308 (C4 (Web Text))

Max Activating Token Index: 57

Text #16

Max Range: 1.8948. Min Range: -1.8948

Max Act: 1.2896. Min Act: -0.0000

Data Index: 1314777 (C4 (Web Text))

Max Activating Token Index: 293

Text #17

Max Range: 1.8948. Min Range: -1.8948

Max Act: 1.3716. Min Act: -0.0000

Data Index: 49078 (C4 (Web Text))

Max Activating Token Index: 742

Text #18

Max Range: 1.8948. Min Range: -1.8948

Max Act: 1.3385. Min Act: -0.0000

Data Index: 631130 (C4 (Web Text))

Max Activating Token Index: 573

Text #19

Max Range: 1.8948. Min Range: -1.8948

Max Act: 1.1795. Min Act: -0.0000

Data Index: 1277561 (C4 (Web Text))

Max Activating Token Index: 518