Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 1558 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.1161. Min Range: -0.1161

Max Act: 0.1161. Min Act: -0.0000

Data Index: 96533 (C4 (Web Text))

Max Activating Token Index: 762

Text #1

Max Range: 0.1161. Min Range: -0.1161

Max Act: 0.1040. Min Act: -0.0000

Data Index: 1311794 (C4 (Web Text))

Max Activating Token Index: 919

Text #2

Max Range: 0.1161. Min Range: -0.1161

Max Act: 0.1033. Min Act: -0.0000

Data Index: 116259 (C4 (Web Text))

Max Activating Token Index: 608

Text #3

Max Range: 0.1161. Min Range: -0.1161

Max Act: 0.1056. Min Act: -0.0000

Data Index: 438092 (C4 (Web Text))

Max Activating Token Index: 945

Text #4

Max Range: 0.1161. Min Range: -0.1161

Max Act: 0.1084. Min Act: -0.0000

Data Index: 640799 (C4 (Web Text))

Max Activating Token Index: 864

Text #5

Max Range: 0.1161. Min Range: -0.1161

Max Act: 0.0994. Min Act: -0.0000

Data Index: 1299216 (C4 (Web Text))

Max Activating Token Index: 526

Text #6

Max Range: 0.1161. Min Range: -0.1161

Max Act: 0.0986. Min Act: -0.0000

Data Index: 938933 (C4 (Web Text))

Max Activating Token Index: 852

Text #7

Max Range: 0.1161. Min Range: -0.1161

Max Act: 0.1045. Min Act: -0.0000

Data Index: 1044012 (C4 (Web Text))

Max Activating Token Index: 983

Text #8

Max Range: 0.1161. Min Range: -0.1161

Max Act: 0.0966. Min Act: -0.0000

Data Index: 703654 (C4 (Web Text))

Max Activating Token Index: 706

Text #9

Max Range: 0.1161. Min Range: -0.1161

Max Act: 0.0935. Min Act: -0.0000

Data Index: 880958 (C4 (Web Text))

Max Activating Token Index: 686

Text #10

Max Range: 0.1161. Min Range: -0.1161

Max Act: 0.1022. Min Act: -0.0000

Data Index: 624705 (C4 (Web Text))

Max Activating Token Index: 587

Text #11

Max Range: 0.1161. Min Range: -0.1161

Max Act: 0.0951. Min Act: -0.0000

Data Index: 105812 (C4 (Web Text))

Max Activating Token Index: 344

Text #12

Max Range: 0.1161. Min Range: -0.1161

Max Act: 0.0874. Min Act: -0.0000

Data Index: 446501 (C4 (Web Text))

Max Activating Token Index: 510

Text #13

Max Range: 0.1161. Min Range: -0.1161

Max Act: 0.0934. Min Act: -0.0000

Data Index: 95826 (C4 (Web Text))

Max Activating Token Index: 673

Text #14

Max Range: 0.1161. Min Range: -0.1161

Max Act: 0.0947. Min Act: -0.0000

Data Index: 191104 (C4 (Web Text))

Max Activating Token Index: 500

Text #15

Max Range: 0.1161. Min Range: -0.1161

Max Act: 0.0842. Min Act: -0.0000

Data Index: 97891 (C4 (Web Text))

Max Activating Token Index: 223

Text #16

Max Range: 0.1161. Min Range: -0.1161

Max Act: 0.0841. Min Act: -0.0000

Data Index: 510575 (C4 (Web Text))

Max Activating Token Index: 447

Text #17

Max Range: 0.1161. Min Range: -0.1161

Max Act: 0.0861. Min Act: -0.0000

Data Index: 203473 (C4 (Web Text))

Max Activating Token Index: 805

Text #18

Max Range: 0.1161. Min Range: -0.1161

Max Act: 0.0844. Min Act: -0.0000

Data Index: 561768 (C4 (Web Text))

Max Activating Token Index: 799

Text #19

Max Range: 0.1161. Min Range: -0.1161

Max Act: 0.0868. Min Act: -0.0000

Data Index: 544829 (C4 (Web Text))

Max Activating Token Index: 874