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

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

Neuron 3992 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 1.2958. Min Range: -1.2958

Max Act: 1.2958. Min Act: -0.0001

Data Index: 690603 (C4 (Web Text))

Max Activating Token Index: 760

Text #1

Max Range: 1.2958. Min Range: -1.2958

Max Act: 1.2414. Min Act: -0.0002

Data Index: 1303592 (C4 (Web Text))

Max Activating Token Index: 750

Text #2

Max Range: 1.2958. Min Range: -1.2958

Max Act: 1.2057. Min Act: -0.0002

Data Index: 970622 (C4 (Web Text))

Max Activating Token Index: 903

Text #3

Max Range: 1.2958. Min Range: -1.2958

Max Act: 1.1757. Min Act: -0.0002

Data Index: 1332500 (C4 (Web Text))

Max Activating Token Index: 794

Text #4

Max Range: 1.2958. Min Range: -1.2958

Max Act: 1.2182. Min Act: -0.0001

Data Index: 19176 (C4 (Web Text))

Max Activating Token Index: 102

Text #5

Max Range: 1.2958. Min Range: -1.2958

Max Act: 1.2113. Min Act: -0.0002

Data Index: 842694 (C4 (Web Text))

Max Activating Token Index: 733

Text #6

Max Range: 1.2958. Min Range: -1.2958

Max Act: 1.1802. Min Act: -0.0002

Data Index: 673375 (C4 (Web Text))

Max Activating Token Index: 418

Text #7

Max Range: 1.2958. Min Range: -1.2958

Max Act: 1.1590. Min Act: -0.0002

Data Index: 365875 (C4 (Web Text))

Max Activating Token Index: 512

Text #8

Max Range: 1.2958. Min Range: -1.2958

Max Act: 1.0883. Min Act: -0.0002

Data Index: 1066121 (C4 (Web Text))

Max Activating Token Index: 771

Text #9

Max Range: 1.2958. Min Range: -1.2958

Max Act: 1.0938. Min Act: -0.0002

Data Index: 92875 (C4 (Web Text))

Max Activating Token Index: 760

Text #10

Max Range: 1.2958. Min Range: -1.2958

Max Act: 1.1443. Min Act: -0.0002

Data Index: 749414 (C4 (Web Text))

Max Activating Token Index: 613

Text #11

Max Range: 1.2958. Min Range: -1.2958

Max Act: 1.1131. Min Act: -0.0002

Data Index: 1230702 (C4 (Web Text))

Max Activating Token Index: 656

Text #12

Max Range: 1.2958. Min Range: -1.2958

Max Act: 1.0846. Min Act: -0.0001

Data Index: 484879 (C4 (Web Text))

Max Activating Token Index: 728

Text #13

Max Range: 1.2958. Min Range: -1.2958

Max Act: 1.1330. Min Act: -0.0002

Data Index: 14519 (C4 (Web Text))

Max Activating Token Index: 547

Text #14

Max Range: 1.2958. Min Range: -1.2958

Max Act: 1.0428. Min Act: -0.0002

Data Index: 232873 (C4 (Web Text))

Max Activating Token Index: 614

Text #15

Max Range: 1.2958. Min Range: -1.2958

Max Act: 1.0567. Min Act: -0.0002

Data Index: 1298025 (C4 (Web Text))

Max Activating Token Index: 490

Text #16

Max Range: 1.2958. Min Range: -1.2958

Max Act: 1.1572. Min Act: -0.0001

Data Index: 478443 (C4 (Web Text))

Max Activating Token Index: 499

Text #17

Max Range: 1.2958. Min Range: -1.2958

Max Act: 1.0837. Min Act: -0.0002

Data Index: 1250124 (C4 (Web Text))

Max Activating Token Index: 936

Text #18

Max Range: 1.2958. Min Range: -1.2958

Max Act: 1.0919. Min Act: -0.0001

Data Index: 438767 (C4 (Web Text))

Max Activating Token Index: 237

Text #19

Max Range: 1.2958. Min Range: -1.2958

Max Act: 1.1122. Min Act: -0.0002

Data Index: 620576 (C4 (Web Text))

Max Activating Token Index: 597