Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 341 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.1121. Min Range: -0.1121

Max Act: 0.1121. Min Act: -0.0005

Data Index: 957816 (C4 (Web Text))

Max Activating Token Index: 441

Text #1

Max Range: 0.1121. Min Range: -0.1121

Max Act: 0.0792. Min Act: -0.0005

Data Index: 347497 (C4 (Web Text))

Max Activating Token Index: 908

Text #2

Max Range: 0.1121. Min Range: -0.1121

Max Act: 0.0839. Min Act: -0.0005

Data Index: 96524 (C4 (Web Text))

Max Activating Token Index: 906

Text #3

Max Range: 0.1121. Min Range: -0.1121

Max Act: 0.0776. Min Act: -0.0005

Data Index: 867940 (C4 (Web Text))

Max Activating Token Index: 864

Text #4

Max Range: 0.1121. Min Range: -0.1121

Max Act: 0.0867. Min Act: -0.0005

Data Index: 361734 (C4 (Web Text))

Max Activating Token Index: 91

Text #5

Max Range: 0.1121. Min Range: -0.1121

Max Act: 0.0814. Min Act: -0.0005

Data Index: 536063 (C4 (Web Text))

Max Activating Token Index: 854

Text #6

Max Range: 0.1121. Min Range: -0.1121

Max Act: 0.0868. Min Act: -0.0005

Data Index: 1234924 (C4 (Web Text))

Max Activating Token Index: 776

Text #7

Max Range: 0.1121. Min Range: -0.1121

Max Act: 0.0824. Min Act: -0.0005

Data Index: 405796 (C4 (Web Text))

Max Activating Token Index: 807

Text #8

Max Range: 0.1121. Min Range: -0.1121

Max Act: 0.0827. Min Act: -0.0005

Data Index: 74407 (C4 (Web Text))

Max Activating Token Index: 396

Text #9

Max Range: 0.1121. Min Range: -0.1121

Max Act: 0.0805. Min Act: -0.0005

Data Index: 705719 (C4 (Web Text))

Max Activating Token Index: 440

Text #10

Max Range: 0.1121. Min Range: -0.1121

Max Act: 0.0835. Min Act: -0.0005

Data Index: 918945 (C4 (Web Text))

Max Activating Token Index: 52

Text #11

Max Range: 0.1121. Min Range: -0.1121

Max Act: 0.0777. Min Act: -0.0005

Data Index: 744971 (C4 (Web Text))

Max Activating Token Index: 854

Text #12

Max Range: 0.1121. Min Range: -0.1121

Max Act: 0.0829. Min Act: -0.0005

Data Index: 803586 (C4 (Web Text))

Max Activating Token Index: 28

Text #13

Max Range: 0.1121. Min Range: -0.1121

Max Act: 0.0791. Min Act: -0.0005

Data Index: 416575 (C4 (Web Text))

Max Activating Token Index: 930

Text #14

Max Range: 0.1121. Min Range: -0.1121

Max Act: 0.0775. Min Act: -0.0005

Data Index: 662167 (C4 (Web Text))

Max Activating Token Index: 87

Text #15

Max Range: 0.1121. Min Range: -0.1121

Max Act: 0.0818. Min Act: -0.0005

Data Index: 561053 (C4 (Web Text))

Max Activating Token Index: 340

Text #16

Max Range: 0.1121. Min Range: -0.1121

Max Act: 0.0822. Min Act: -0.0005

Data Index: 1034984 (C4 (Web Text))

Max Activating Token Index: 784

Text #17

Max Range: 0.1121. Min Range: -0.1121

Max Act: 0.0788. Min Act: -0.0005

Data Index: 77230 (C4 (Web Text))

Max Activating Token Index: 388

Text #18

Max Range: 0.1121. Min Range: -0.1121

Max Act: 0.0799. Min Act: -0.0005

Data Index: 66248 (C4 (Web Text))

Max Activating Token Index: 299

Text #19

Max Range: 0.1121. Min Range: -0.1121

Max Act: 0.0777. Min Act: -0.0005

Data Index: 637225 (C4 (Web Text))

Max Activating Token Index: 967