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

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

Neuron 406 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: 4.3164. Min Range: -4.3164

Max Act: 4.1821. Min Act: -0.0001

Data Index: 771370 (C4 (Web Text))

Max Activating Token Index: 504

Text #1

Max Range: 4.3164. Min Range: -4.3164

Max Act: 3.8548. Min Act: -0.0001

Data Index: 356705 (C4 (Web Text))

Max Activating Token Index: 378

Text #2

Max Range: 4.3164. Min Range: -4.3164

Max Act: 4.3164. Min Act: -0.0001

Data Index: 609143 (C4 (Web Text))

Max Activating Token Index: 230

Text #3

Max Range: 4.3164. Min Range: -4.3164

Max Act: 3.9624. Min Act: -0.0001

Data Index: 1270957 (C4 (Web Text))

Max Activating Token Index: 783

Text #4

Max Range: 4.3164. Min Range: -4.3164

Max Act: 3.9721. Min Act: -0.0001

Data Index: 765587 (C4 (Web Text))

Max Activating Token Index: 965

Text #5

Max Range: 4.3164. Min Range: -4.3164

Max Act: 4.2007. Min Act: -0.0001

Data Index: 544305 (C4 (Web Text))

Max Activating Token Index: 504

Text #6

Max Range: 4.3164. Min Range: -4.3164

Max Act: 3.8650. Min Act: -0.0001

Data Index: 238255 (C4 (Web Text))

Max Activating Token Index: 817

Text #7

Max Range: 4.3164. Min Range: -4.3164

Max Act: 4.0083. Min Act: -0.0001

Data Index: 676394 (C4 (Web Text))

Max Activating Token Index: 206

Text #8

Max Range: 4.3164. Min Range: -4.3164

Max Act: 3.9608. Min Act: -0.0001

Data Index: 94106 (C4 (Web Text))

Max Activating Token Index: 970

Text #9

Max Range: 4.3164. Min Range: -4.3164

Max Act: 3.7788. Min Act: -0.0001

Data Index: 563251 (C4 (Web Text))

Max Activating Token Index: 451

Text #10

Max Range: 4.3164. Min Range: -4.3164

Max Act: 3.8781. Min Act: -0.0001

Data Index: 12237 (C4 (Web Text))

Max Activating Token Index: 337

Text #11

Max Range: 4.3164. Min Range: -4.3164

Max Act: 3.8371. Min Act: -0.0001

Data Index: 935208 (C4 (Web Text))

Max Activating Token Index: 563

Text #12

Max Range: 4.3164. Min Range: -4.3164

Max Act: 3.5819. Min Act: -0.0001

Data Index: 212920 (C4 (Web Text))

Max Activating Token Index: 813

Text #13

Max Range: 4.3164. Min Range: -4.3164

Max Act: 3.5754. Min Act: -0.0001

Data Index: 361386 (C4 (Web Text))

Max Activating Token Index: 927

Text #14

Max Range: 4.3164. Min Range: -4.3164

Max Act: 3.2576. Min Act: -0.0001

Data Index: 1076358 (C4 (Web Text))

Max Activating Token Index: 775

Text #15

Max Range: 4.3164. Min Range: -4.3164

Max Act: 3.7507. Min Act: -0.0001

Data Index: 573079 (C4 (Web Text))

Max Activating Token Index: 567

Text #16

Max Range: 4.3164. Min Range: -4.3164

Max Act: 3.5399. Min Act: -0.0001

Data Index: 449249 (C4 (Web Text))

Max Activating Token Index: 154

Text #17

Max Range: 4.3164. Min Range: -4.3164

Max Act: 3.5306. Min Act: -0.0001

Data Index: 1289744 (C4 (Web Text))

Max Activating Token Index: 243

Text #18

Max Range: 4.3164. Min Range: -4.3164

Max Act: 3.5332. Min Act: -0.0001

Data Index: 451852 (C4 (Web Text))

Max Activating Token Index: 457

Text #19

Max Range: 4.3164. Min Range: -4.3164

Max Act: 3.1811. Min Act: -0.0001

Data Index: 816794 (C4 (Web Text))

Max Activating Token Index: 684