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

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

Neuron 5912 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8938. Min Range: -0.8938

Max Act: 0.8938. Min Act: -0.0002

Data Index: 853810 (C4 (Web Text))

Max Activating Token Index: 297

Text #1

Max Range: 0.8938. Min Range: -0.8938

Max Act: 0.8598. Min Act: -0.0002

Data Index: 241096 (C4 (Web Text))

Max Activating Token Index: 279

Text #2

Max Range: 0.8938. Min Range: -0.8938

Max Act: 0.8716. Min Act: -0.0002

Data Index: 1118417 (C4 (Web Text))

Max Activating Token Index: 512

Text #3

Max Range: 0.8938. Min Range: -0.8938

Max Act: 0.8394. Min Act: -0.0002

Data Index: 561055 (C4 (Web Text))

Max Activating Token Index: 445

Text #4

Max Range: 0.8938. Min Range: -0.8938

Max Act: 0.8317. Min Act: -0.0002

Data Index: 125537 (C4 (Web Text))

Max Activating Token Index: 216

Text #5

Max Range: 0.8938. Min Range: -0.8938

Max Act: 0.8220. Min Act: -0.0002

Data Index: 571587 (C4 (Web Text))

Max Activating Token Index: 397

Text #6

Max Range: 0.8938. Min Range: -0.8938

Max Act: 0.8105. Min Act: -0.0002

Data Index: 695065 (C4 (Web Text))

Max Activating Token Index: 285

Text #7

Max Range: 0.8938. Min Range: -0.8938

Max Act: 0.8327. Min Act: -0.0002

Data Index: 183383 (C4 (Web Text))

Max Activating Token Index: 427

Text #8

Max Range: 0.8938. Min Range: -0.8938

Max Act: 0.7737. Min Act: -0.0002

Data Index: 517719 (C4 (Web Text))

Max Activating Token Index: 873

Text #9

Max Range: 0.8938. Min Range: -0.8938

Max Act: 0.7903. Min Act: -0.0002

Data Index: 1288193 (C4 (Web Text))

Max Activating Token Index: 547

Text #10

Max Range: 0.8938. Min Range: -0.8938

Max Act: 0.7867. Min Act: -0.0002

Data Index: 623928 (C4 (Web Text))

Max Activating Token Index: 664

Text #11

Max Range: 0.8938. Min Range: -0.8938

Max Act: 0.7793. Min Act: -0.0002

Data Index: 1251933 (C4 (Web Text))

Max Activating Token Index: 453

Text #12

Max Range: 0.8938. Min Range: -0.8938

Max Act: 0.8120. Min Act: -0.0002

Data Index: 990449 (C4 (Web Text))

Max Activating Token Index: 859

Text #13

Max Range: 0.8938. Min Range: -0.8938

Max Act: 0.7781. Min Act: -0.0002

Data Index: 1340339 (C4 (Web Text))

Max Activating Token Index: 72

Text #14

Max Range: 0.8938. Min Range: -0.8938

Max Act: 0.7750. Min Act: -0.0002

Data Index: 33962 (C4 (Web Text))

Max Activating Token Index: 279

Text #15

Max Range: 0.8938. Min Range: -0.8938

Max Act: 0.7717. Min Act: -0.0002

Data Index: 575188 (C4 (Web Text))

Max Activating Token Index: 694

Text #16

Max Range: 0.8938. Min Range: -0.8938

Max Act: 0.7542. Min Act: -0.0002

Data Index: 1358017 (C4 (Web Text))

Max Activating Token Index: 500

Text #17

Max Range: 0.8938. Min Range: -0.8938

Max Act: 0.7532. Min Act: -0.0002

Data Index: 646514 (C4 (Web Text))

Max Activating Token Index: 464

Text #18

Max Range: 0.8938. Min Range: -0.8938

Max Act: 0.7456. Min Act: -0.0002

Data Index: 1121195 (C4 (Web Text))

Max Activating Token Index: 244

Text #19

Max Range: 0.8938. Min Range: -0.8938

Max Act: 0.7468. Min Act: -0.0002

Data Index: 989183 (C4 (Web Text))

Max Activating Token Index: 338