Model: SoLU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 1200 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')

Text #0

Max Range: 0.0936. Min Range: -0.0936

Max Act: 0.0936. Min Act: -0.0006

Data Index: 420868 (C4 (Web Text))

Max Activating Token Index: 472

Text #1

Max Range: 0.0936. Min Range: -0.0936

Max Act: 0.0884. Min Act: -0.0006

Data Index: 500466 (C4 (Web Text))

Max Activating Token Index: 992

Text #2

Max Range: 0.0936. Min Range: -0.0936

Max Act: 0.0903. Min Act: -0.0006

Data Index: 1344663 (C4 (Web Text))

Max Activating Token Index: 204

Text #3

Max Range: 0.0936. Min Range: -0.0936

Max Act: 0.0830. Min Act: -0.0006

Data Index: 454823 (C4 (Web Text))

Max Activating Token Index: 359

Text #4

Max Range: 0.0936. Min Range: -0.0936

Max Act: 0.0815. Min Act: -0.0006

Data Index: 248819 (C4 (Web Text))

Max Activating Token Index: 681

Text #5

Max Range: 0.0936. Min Range: -0.0936

Max Act: 0.0860. Min Act: -0.0006

Data Index: 785102 (C4 (Web Text))

Max Activating Token Index: 416

Text #6

Max Range: 0.0936. Min Range: -0.0936

Max Act: 0.0812. Min Act: -0.0006

Data Index: 1177687 (C4 (Web Text))

Max Activating Token Index: 175

Text #7

Max Range: 0.0936. Min Range: -0.0936

Max Act: 0.0805. Min Act: -0.0006

Data Index: 1138070 (C4 (Web Text))

Max Activating Token Index: 669

Text #8

Max Range: 0.0936. Min Range: -0.0936

Max Act: 0.0810. Min Act: -0.0006

Data Index: 765861 (C4 (Web Text))

Max Activating Token Index: 74

Text #9

Max Range: 0.0936. Min Range: -0.0936

Max Act: 0.0822. Min Act: -0.0006

Data Index: 280307 (C4 (Web Text))

Max Activating Token Index: 796

Text #10

Max Range: 0.0936. Min Range: -0.0936

Max Act: 0.0786. Min Act: -0.0006

Data Index: 419073 (C4 (Web Text))

Max Activating Token Index: 299

Text #11

Max Range: 0.0936. Min Range: -0.0936

Max Act: 0.0779. Min Act: -0.0006

Data Index: 440472 (C4 (Web Text))

Max Activating Token Index: 148

Text #12

Max Range: 0.0936. Min Range: -0.0936

Max Act: 0.0792. Min Act: -0.0006

Data Index: 1250384 (C4 (Web Text))

Max Activating Token Index: 220

Text #13

Max Range: 0.0936. Min Range: -0.0936

Max Act: 0.0818. Min Act: -0.0006

Data Index: 1120223 (C4 (Web Text))

Max Activating Token Index: 487

Text #14

Max Range: 0.0936. Min Range: -0.0936

Max Act: 0.0757. Min Act: -0.0006

Data Index: 397427 (C4 (Web Text))

Max Activating Token Index: 383

Text #15

Max Range: 0.0936. Min Range: -0.0936

Max Act: 0.0757. Min Act: -0.0005

Data Index: 817265 (C4 (Web Text))

Max Activating Token Index: 287

Text #16

Max Range: 0.0936. Min Range: -0.0936

Max Act: 0.0784. Min Act: -0.0006

Data Index: 355419 (C4 (Web Text))

Max Activating Token Index: 260

Text #17

Max Range: 0.0936. Min Range: -0.0936

Max Act: 0.0789. Min Act: -0.0006

Data Index: 1025762 (C4 (Web Text))

Max Activating Token Index: 136

Text #18

Max Range: 0.0936. Min Range: -0.0936

Max Act: 0.0765. Min Act: -0.0006

Data Index: 1089494 (C4 (Web Text))

Max Activating Token Index: 648

Text #19

Max Range: 0.0936. Min Range: -0.0936

Max Act: 0.0782. Min Act: -0.0006

Data Index: 1342841 (C4 (Web Text))

Max Activating Token Index: 447