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

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

Neuron 3956 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3231. Min Range: -0.3231

Max Act: 0.3168. Min Act: -0.0001

Data Index: 183555 (C4 (Web Text))

Max Activating Token Index: 677

Text #1

Max Range: 0.3231. Min Range: -0.3231

Max Act: 0.3231. Min Act: -0.0001

Data Index: 442636 (C4 (Web Text))

Max Activating Token Index: 893

Text #2

Max Range: 0.3231. Min Range: -0.3231

Max Act: 0.3113. Min Act: -0.0001

Data Index: 423822 (C4 (Web Text))

Max Activating Token Index: 288

Text #3

Max Range: 0.3231. Min Range: -0.3231

Max Act: 0.3101. Min Act: -0.0001

Data Index: 781738 (C4 (Web Text))

Max Activating Token Index: 762

Text #4

Max Range: 0.3231. Min Range: -0.3231

Max Act: 0.2938. Min Act: -0.0001

Data Index: 510618 (C4 (Web Text))

Max Activating Token Index: 345

Text #5

Max Range: 0.3231. Min Range: -0.3231

Max Act: 0.2948. Min Act: -0.0001

Data Index: 570352 (C4 (Web Text))

Max Activating Token Index: 27

Text #6

Max Range: 0.3231. Min Range: -0.3231

Max Act: 0.3138. Min Act: -0.0001

Data Index: 854772 (C4 (Web Text))

Max Activating Token Index: 913

Text #7

Max Range: 0.3231. Min Range: -0.3231

Max Act: 0.2818. Min Act: -0.0001

Data Index: 1218943 (C4 (Web Text))

Max Activating Token Index: 449

Text #8

Max Range: 0.3231. Min Range: -0.3231

Max Act: 0.2699. Min Act: -0.0001

Data Index: 140933 (C4 (Web Text))

Max Activating Token Index: 107

Text #9

Max Range: 0.3231. Min Range: -0.3231

Max Act: 0.2870. Min Act: -0.0001

Data Index: 368784 (C4 (Web Text))

Max Activating Token Index: 13

Text #10

Max Range: 0.3231. Min Range: -0.3231

Max Act: 0.2920. Min Act: -0.0001

Data Index: 284654 (C4 (Web Text))

Max Activating Token Index: 624

Text #11

Max Range: 0.3231. Min Range: -0.3231

Max Act: 0.2659. Min Act: -0.0001

Data Index: 757950 (C4 (Web Text))

Max Activating Token Index: 772

Text #12

Max Range: 0.3231. Min Range: -0.3231

Max Act: 0.2804. Min Act: -0.0001

Data Index: 518116 (C4 (Web Text))

Max Activating Token Index: 166

Text #13

Max Range: 0.3231. Min Range: -0.3231

Max Act: 0.2829. Min Act: -0.0001

Data Index: 608825 (C4 (Web Text))

Max Activating Token Index: 558

Text #14

Max Range: 0.3231. Min Range: -0.3231

Max Act: 0.2773. Min Act: -0.0001

Data Index: 1329928 (C4 (Web Text))

Max Activating Token Index: 186

Text #15

Max Range: 0.3231. Min Range: -0.3231

Max Act: 0.2880. Min Act: -0.0001

Data Index: 1045657 (C4 (Web Text))

Max Activating Token Index: 301

Text #16

Max Range: 0.3231. Min Range: -0.3231

Max Act: 0.2765. Min Act: -0.0001

Data Index: 177622 (C4 (Web Text))

Max Activating Token Index: 455

Text #17

Max Range: 0.3231. Min Range: -0.3231

Max Act: 0.3066. Min Act: -0.0001

Data Index: 278172 (C4 (Web Text))

Max Activating Token Index: 819

Text #18

Max Range: 0.3231. Min Range: -0.3231

Max Act: 0.2818. Min Act: -0.0001

Data Index: 897664 (C4 (Web Text))

Max Activating Token Index: 758

Text #19

Max Range: 0.3231. Min Range: -0.3231

Max Act: 0.2717. Min Act: -0.0001

Data Index: 532131 (C4 (Web Text))

Max Activating Token Index: 314