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

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

Neuron 955 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: 0.1271. Min Range: -0.1271

Max Act: 0.1271. Min Act: -0.0002

Data Index: 754495 (C4 (Web Text))

Max Activating Token Index: 14

Text #1

Max Range: 0.1271. Min Range: -0.1271

Max Act: 0.0942. Min Act: -0.0002

Data Index: 517887 (C4 (Web Text))

Max Activating Token Index: 1023

Text #2

Max Range: 0.1271. Min Range: -0.1271

Max Act: 0.0951. Min Act: -0.0002

Data Index: 15445 (C4 (Web Text))

Max Activating Token Index: 75

Text #3

Max Range: 0.1271. Min Range: -0.1271

Max Act: 0.0875. Min Act: -0.0002

Data Index: 382843 (C4 (Web Text))

Max Activating Token Index: 97

Text #4

Max Range: 0.1271. Min Range: -0.1271

Max Act: 0.0912. Min Act: -0.0002

Data Index: 963070 (C4 (Web Text))

Max Activating Token Index: 800

Text #5

Max Range: 0.1271. Min Range: -0.1271

Max Act: 0.0863. Min Act: -0.0002

Data Index: 79910 (C4 (Web Text))

Max Activating Token Index: 116

Text #6

Max Range: 0.1271. Min Range: -0.1271

Max Act: 0.0899. Min Act: -0.0002

Data Index: 288270 (C4 (Web Text))

Max Activating Token Index: 689

Text #7

Max Range: 0.1271. Min Range: -0.1271

Max Act: 0.0928. Min Act: -0.0002

Data Index: 83304 (C4 (Web Text))

Max Activating Token Index: 139

Text #8

Max Range: 0.1271. Min Range: -0.1271

Max Act: 0.0859. Min Act: -0.0002

Data Index: 226580 (C4 (Web Text))

Max Activating Token Index: 404

Text #9

Max Range: 0.1271. Min Range: -0.1271

Max Act: 0.0874. Min Act: -0.0002

Data Index: 347773 (C4 (Web Text))

Max Activating Token Index: 367

Text #10

Max Range: 0.1271. Min Range: -0.1271

Max Act: 0.0877. Min Act: -0.0002

Data Index: 974136 (C4 (Web Text))

Max Activating Token Index: 447

Text #11

Max Range: 0.1271. Min Range: -0.1271

Max Act: 0.0862. Min Act: -0.0002

Data Index: 1104884 (C4 (Web Text))

Max Activating Token Index: 35

Text #12

Max Range: 0.1271. Min Range: -0.1271

Max Act: 0.0880. Min Act: -0.0002

Data Index: 877750 (C4 (Web Text))

Max Activating Token Index: 855

Text #13

Max Range: 0.1271. Min Range: -0.1271

Max Act: 0.0862. Min Act: -0.0002

Data Index: 623109 (C4 (Web Text))

Max Activating Token Index: 484

Text #14

Max Range: 0.1271. Min Range: -0.1271

Max Act: 0.0861. Min Act: -0.0002

Data Index: 56078 (C4 (Web Text))

Max Activating Token Index: 238

Text #15

Max Range: 0.1271. Min Range: -0.1271

Max Act: 0.0821. Min Act: -0.0002

Data Index: 45079 (C4 (Web Text))

Max Activating Token Index: 30

Text #16

Max Range: 0.1271. Min Range: -0.1271

Max Act: 0.0907. Min Act: -0.0002

Data Index: 478739 (C4 (Web Text))

Max Activating Token Index: 431

Text #17

Max Range: 0.1271. Min Range: -0.1271

Max Act: 0.0873. Min Act: -0.0002

Data Index: 549087 (C4 (Web Text))

Max Activating Token Index: 214

Text #18

Max Range: 0.1271. Min Range: -0.1271

Max Act: 0.0882. Min Act: -0.0002

Data Index: 182183 (C4 (Web Text))

Max Activating Token Index: 519

Text #19

Max Range: 0.1271. Min Range: -0.1271

Max Act: 0.0828. Min Act: -0.0002

Data Index: 622262 (C4 (Web Text))

Max Activating Token Index: 309