Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 5311 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 3.0148. Min Range: -3.0148

Max Act: 3.0148. Min Act: -0.0000

Data Index: 252733 (C4 (Web Text))

Max Activating Token Index: 830

Text #1

Max Range: 3.0148. Min Range: -3.0148

Max Act: 2.9680. Min Act: -0.0000

Data Index: 1104872 (C4 (Web Text))

Max Activating Token Index: 572

Text #2

Max Range: 3.0148. Min Range: -3.0148

Max Act: 2.9628. Min Act: -0.0000

Data Index: 483701 (C4 (Web Text))

Max Activating Token Index: 817

Text #3

Max Range: 3.0148. Min Range: -3.0148

Max Act: 2.6801. Min Act: -0.0000

Data Index: 827736 (C4 (Web Text))

Max Activating Token Index: 799

Text #4

Max Range: 3.0148. Min Range: -3.0148

Max Act: 2.6401. Min Act: -0.0000

Data Index: 827364 (C4 (Web Text))

Max Activating Token Index: 132

Text #5

Max Range: 3.0148. Min Range: -3.0148

Max Act: 2.4883. Min Act: -0.0000

Data Index: 633007 (C4 (Web Text))

Max Activating Token Index: 216

Text #6

Max Range: 3.0148. Min Range: -3.0148

Max Act: 2.4512. Min Act: -0.0000

Data Index: 863643 (C4 (Web Text))

Max Activating Token Index: 245

Text #7

Max Range: 3.0148. Min Range: -3.0148

Max Act: 2.6039. Min Act: -0.0000

Data Index: 1224605 (C4 (Web Text))

Max Activating Token Index: 278

Text #8

Max Range: 3.0148. Min Range: -3.0148

Max Act: 2.5491. Min Act: -0.0000

Data Index: 645548 (C4 (Web Text))

Max Activating Token Index: 636

Text #9

Max Range: 3.0148. Min Range: -3.0148

Max Act: 2.6645. Min Act: -0.0000

Data Index: 468314 (C4 (Web Text))

Max Activating Token Index: 931

Text #10

Max Range: 3.0148. Min Range: -3.0148

Max Act: 2.5192. Min Act: -0.0000

Data Index: 355664 (C4 (Web Text))

Max Activating Token Index: 683

Text #11

Max Range: 3.0148. Min Range: -3.0148

Max Act: 2.5074. Min Act: -0.0000

Data Index: 811673 (C4 (Web Text))

Max Activating Token Index: 561

Text #12

Max Range: 3.0148. Min Range: -3.0148

Max Act: 2.4818. Min Act: -0.0000

Data Index: 378761 (C4 (Web Text))

Max Activating Token Index: 565

Text #13

Max Range: 3.0148. Min Range: -3.0148

Max Act: 2.4843. Min Act: -0.0000

Data Index: 820454 (C4 (Web Text))

Max Activating Token Index: 125

Text #14

Max Range: 3.0148. Min Range: -3.0148

Max Act: 2.4474. Min Act: -0.0000

Data Index: 724160 (C4 (Web Text))

Max Activating Token Index: 399

Text #15

Max Range: 3.0148. Min Range: -3.0148

Max Act: 2.2961. Min Act: -0.0000

Data Index: 1016297 (C4 (Web Text))

Max Activating Token Index: 846

Text #16

Max Range: 3.0148. Min Range: -3.0148

Max Act: 2.4082. Min Act: -0.0000

Data Index: 1213449 (C4 (Web Text))

Max Activating Token Index: 742

Text #17

Max Range: 3.0148. Min Range: -3.0148

Max Act: 2.2870. Min Act: -0.0000

Data Index: 638843 (C4 (Web Text))

Max Activating Token Index: 687

Text #18

Max Range: 3.0148. Min Range: -3.0148

Max Act: 2.3619. Min Act: -0.0000

Data Index: 1107053 (C4 (Web Text))

Max Activating Token Index: 841

Text #19

Max Range: 3.0148. Min Range: -3.0148

Max Act: 2.2335. Min Act: -0.0000

Data Index: 1217010 (C4 (Web Text))

Max Activating Token Index: 686