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

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

Neuron 749 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0933. Min Range: -0.0933

Max Act: 0.0915. Min Act: -0.0002

Data Index: 1204964 (C4 (Web Text))

Max Activating Token Index: 19

Text #1

Max Range: 0.0933. Min Range: -0.0933

Max Act: 0.0925. Min Act: -0.0002

Data Index: 249088 (C4 (Web Text))

Max Activating Token Index: 562

Text #2

Max Range: 0.0933. Min Range: -0.0933

Max Act: 0.0821. Min Act: -0.0002

Data Index: 537223 (C4 (Web Text))

Max Activating Token Index: 160

Text #3

Max Range: 0.0933. Min Range: -0.0933

Max Act: 0.0933. Min Act: -0.0002

Data Index: 944948 (C4 (Web Text))

Max Activating Token Index: 844

Text #4

Max Range: 0.0933. Min Range: -0.0933

Max Act: 0.0852. Min Act: -0.0002

Data Index: 921229 (C4 (Web Text))

Max Activating Token Index: 58

Text #5

Max Range: 0.0933. Min Range: -0.0933

Max Act: 0.0860. Min Act: -0.0002

Data Index: 1282263 (C4 (Web Text))

Max Activating Token Index: 808

Text #6

Max Range: 0.0933. Min Range: -0.0933

Max Act: 0.0827. Min Act: -0.0002

Data Index: 1064939 (C4 (Web Text))

Max Activating Token Index: 869

Text #7

Max Range: 0.0933. Min Range: -0.0933

Max Act: 0.0837. Min Act: -0.0002

Data Index: 723223 (C4 (Web Text))

Max Activating Token Index: 1016

Text #8

Max Range: 0.0933. Min Range: -0.0933

Max Act: 0.0818. Min Act: -0.0002

Data Index: 106593 (C4 (Web Text))

Max Activating Token Index: 237

Text #9

Max Range: 0.0933. Min Range: -0.0933

Max Act: 0.0825. Min Act: -0.0002

Data Index: 707225 (C4 (Web Text))

Max Activating Token Index: 974

Text #10

Max Range: 0.0933. Min Range: -0.0933

Max Act: 0.0780. Min Act: -0.0002

Data Index: 313332 (C4 (Web Text))

Max Activating Token Index: 858

Text #11

Max Range: 0.0933. Min Range: -0.0933

Max Act: 0.0824. Min Act: -0.0002

Data Index: 735669 (C4 (Web Text))

Max Activating Token Index: 433

Text #12

Max Range: 0.0933. Min Range: -0.0933

Max Act: 0.0791. Min Act: -0.0002

Data Index: 1245204 (C4 (Web Text))

Max Activating Token Index: 257

Text #13

Max Range: 0.0933. Min Range: -0.0933

Max Act: 0.0804. Min Act: -0.0002

Data Index: 48624 (C4 (Web Text))

Max Activating Token Index: 720

Text #14

Max Range: 0.0933. Min Range: -0.0933

Max Act: 0.0801. Min Act: -0.0002

Data Index: 1034415 (C4 (Web Text))

Max Activating Token Index: 943

Text #15

Max Range: 0.0933. Min Range: -0.0933

Max Act: 0.0752. Min Act: -0.0002

Data Index: 560506 (C4 (Web Text))

Max Activating Token Index: 771

Text #16

Max Range: 0.0933. Min Range: -0.0933

Max Act: 0.0786. Min Act: -0.0002

Data Index: 796000 (C4 (Web Text))

Max Activating Token Index: 698

Text #17

Max Range: 0.0933. Min Range: -0.0933

Max Act: 0.0807. Min Act: -0.0002

Data Index: 627137 (C4 (Web Text))

Max Activating Token Index: 286

Text #18

Max Range: 0.0933. Min Range: -0.0933

Max Act: 0.0722. Min Act: -0.0002

Data Index: 793332 (C4 (Web Text))

Max Activating Token Index: 873

Text #19

Max Range: 0.0933. Min Range: -0.0933

Max Act: 0.0810. Min Act: -0.0002

Data Index: 823092 (C4 (Web Text))

Max Activating Token Index: 540