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

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

Neuron 4768 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: 0.1924. Min Range: -0.1924

Max Act: 0.1924. Min Act: -0.0002

Data Index: 1112932 (C4 (Web Text))

Max Activating Token Index: 153

Text #1

Max Range: 0.1924. Min Range: -0.1924

Max Act: 0.1467. Min Act: -0.0002

Data Index: 119528 (C4 (Web Text))

Max Activating Token Index: 669

Text #2

Max Range: 0.1924. Min Range: -0.1924

Max Act: 0.1403. Min Act: -0.0002

Data Index: 637733 (C4 (Web Text))

Max Activating Token Index: 495

Text #3

Max Range: 0.1924. Min Range: -0.1924

Max Act: 0.1123. Min Act: -0.0002

Data Index: 879909 (C4 (Web Text))

Max Activating Token Index: 266

Text #4

Max Range: 0.1924. Min Range: -0.1924

Max Act: 0.1026. Min Act: -0.0002

Data Index: 561992 (C4 (Web Text))

Max Activating Token Index: 363

Text #5

Max Range: 0.1924. Min Range: -0.1924

Max Act: 0.1026. Min Act: -0.0002

Data Index: 321490 (C4 (Web Text))

Max Activating Token Index: 714

Text #6

Max Range: 0.1924. Min Range: -0.1924

Max Act: 0.0946. Min Act: -0.0002

Data Index: 602864 (C4 (Web Text))

Max Activating Token Index: 309

Text #7

Max Range: 0.1924. Min Range: -0.1924

Max Act: 0.0993. Min Act: -0.0002

Data Index: 1236268 (C4 (Web Text))

Max Activating Token Index: 749

Text #8

Max Range: 0.1924. Min Range: -0.1924

Max Act: 0.0947. Min Act: -0.0002

Data Index: 632702 (C4 (Web Text))

Max Activating Token Index: 199

Text #9

Max Range: 0.1924. Min Range: -0.1924

Max Act: 0.0945. Min Act: -0.0002

Data Index: 79729 (C4 (Web Text))

Max Activating Token Index: 771

Text #10

Max Range: 0.1924. Min Range: -0.1924

Max Act: 0.0929. Min Act: -0.0001

Data Index: 476900 (C4 (Web Text))

Max Activating Token Index: 80

Text #11

Max Range: 0.1924. Min Range: -0.1924

Max Act: 0.0909. Min Act: -0.0002

Data Index: 685589 (C4 (Web Text))

Max Activating Token Index: 474

Text #12

Max Range: 0.1924. Min Range: -0.1924

Max Act: 0.0903. Min Act: -0.0002

Data Index: 602381 (C4 (Web Text))

Max Activating Token Index: 481

Text #13

Max Range: 0.1924. Min Range: -0.1924

Max Act: 0.0866. Min Act: -0.0002

Data Index: 298078 (C4 (Web Text))

Max Activating Token Index: 402

Text #14

Max Range: 0.1924. Min Range: -0.1924

Max Act: 0.0851. Min Act: -0.0002

Data Index: 444246 (C4 (Web Text))

Max Activating Token Index: 127

Text #15

Max Range: 0.1924. Min Range: -0.1924

Max Act: 0.0853. Min Act: -0.0002

Data Index: 495857 (C4 (Web Text))

Max Activating Token Index: 674

Text #16

Max Range: 0.1924. Min Range: -0.1924

Max Act: 0.0804. Min Act: -0.0002

Data Index: 492014 (C4 (Web Text))

Max Activating Token Index: 278

Text #17

Max Range: 0.1924. Min Range: -0.1924

Max Act: 0.0833. Min Act: -0.0002

Data Index: 362852 (C4 (Web Text))

Max Activating Token Index: 263

Text #18

Max Range: 0.1924. Min Range: -0.1924

Max Act: 0.0790. Min Act: -0.0002

Data Index: 640381 (C4 (Web Text))

Max Activating Token Index: 958

Text #19

Max Range: 0.1924. Min Range: -0.1924

Max Act: 0.0808. Min Act: -0.0002

Data Index: 570541 (C4 (Web Text))

Max Activating Token Index: 157