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

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

Neuron 5558 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9869. Min Range: -0.9869

Max Act: 0.9691. Min Act: -0.0001

Data Index: 705660 (C4 (Web Text))

Max Activating Token Index: 520

Text #1

Max Range: 0.9869. Min Range: -0.9869

Max Act: 0.9019. Min Act: -0.0002

Data Index: 242116 (C4 (Web Text))

Max Activating Token Index: 856

Text #2

Max Range: 0.9869. Min Range: -0.9869

Max Act: 0.8457. Min Act: -0.0001

Data Index: 1001937 (C4 (Web Text))

Max Activating Token Index: 413

Text #3

Max Range: 0.9869. Min Range: -0.9869

Max Act: 0.6350. Min Act: -0.0001

Data Index: 82523 (C4 (Web Text))

Max Activating Token Index: 789

Text #4

Max Range: 0.9869. Min Range: -0.9869

Max Act: 0.9869. Min Act: -0.0002

Data Index: 866397 (C4 (Web Text))

Max Activating Token Index: 728

Text #5

Max Range: 0.9869. Min Range: -0.9869

Max Act: 0.9299. Min Act: -0.0002

Data Index: 70256 (C4 (Web Text))

Max Activating Token Index: 470

Text #6

Max Range: 0.9869. Min Range: -0.9869

Max Act: 0.7448. Min Act: -0.0001

Data Index: 382844 (C4 (Web Text))

Max Activating Token Index: 807

Text #7

Max Range: 0.9869. Min Range: -0.9869

Max Act: 0.9093. Min Act: -0.0001

Data Index: 1007254 (C4 (Web Text))

Max Activating Token Index: 238

Text #8

Max Range: 0.9869. Min Range: -0.9869

Max Act: 0.8065. Min Act: -0.0001

Data Index: 957718 (C4 (Web Text))

Max Activating Token Index: 205

Text #9

Max Range: 0.9869. Min Range: -0.9869

Max Act: 0.7543. Min Act: -0.0001

Data Index: 936593 (C4 (Web Text))

Max Activating Token Index: 982

Text #10

Max Range: 0.9869. Min Range: -0.9869

Max Act: 0.7655. Min Act: -0.0001

Data Index: 500397 (C4 (Web Text))

Max Activating Token Index: 390

Text #11

Max Range: 0.9869. Min Range: -0.9869

Max Act: 0.6913. Min Act: -0.0001

Data Index: 83524 (C4 (Web Text))

Max Activating Token Index: 343

Text #12

Max Range: 0.9869. Min Range: -0.9869

Max Act: 0.7760. Min Act: -0.0001

Data Index: 893768 (C4 (Web Text))

Max Activating Token Index: 447

Text #13

Max Range: 0.9869. Min Range: -0.9869

Max Act: 0.8453. Min Act: -0.0001

Data Index: 468222 (C4 (Web Text))

Max Activating Token Index: 34

Text #14

Max Range: 0.9869. Min Range: -0.9869

Max Act: 0.7552. Min Act: -0.0001

Data Index: 153248 (C4 (Web Text))

Max Activating Token Index: 240

Text #15

Max Range: 0.9869. Min Range: -0.9869

Max Act: 0.7626. Min Act: -0.0002

Data Index: 1087513 (C4 (Web Text))

Max Activating Token Index: 558

Text #16

Max Range: 0.9869. Min Range: -0.9869

Max Act: 0.7547. Min Act: -0.0001

Data Index: 990117 (C4 (Web Text))

Max Activating Token Index: 569

Text #17

Max Range: 0.9869. Min Range: -0.9869

Max Act: 0.7929. Min Act: -0.0001

Data Index: 408690 (C4 (Web Text))

Max Activating Token Index: 97

Text #18

Max Range: 0.9869. Min Range: -0.9869

Max Act: 0.6275. Min Act: -0.0001

Data Index: 1028001 (C4 (Web Text))

Max Activating Token Index: 337

Text #19

Max Range: 0.9869. Min Range: -0.9869

Max Act: 0.7449. Min Act: -0.0001

Data Index: 1041586 (C4 (Web Text))

Max Activating Token Index: 298