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

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

Neuron 716 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.1404. Min Range: -2.1404

Max Act: 2.1404. Min Act: -0.0000

Data Index: 448383 (C4 (Web Text))

Max Activating Token Index: 627

Text #1

Max Range: 2.1404. Min Range: -2.1404

Max Act: 2.0994. Min Act: -0.0000

Data Index: 957809 (C4 (Web Text))

Max Activating Token Index: 947

Text #2

Max Range: 2.1404. Min Range: -2.1404

Max Act: 1.8749. Min Act: -0.0000

Data Index: 218163 (C4 (Web Text))

Max Activating Token Index: 724

Text #3

Max Range: 2.1404. Min Range: -2.1404

Max Act: 1.8942. Min Act: -0.0000

Data Index: 341264 (C4 (Web Text))

Max Activating Token Index: 384

Text #4

Max Range: 2.1404. Min Range: -2.1404

Max Act: 1.7941. Min Act: -0.0000

Data Index: 787762 (C4 (Web Text))

Max Activating Token Index: 761

Text #5

Max Range: 2.1404. Min Range: -2.1404

Max Act: 1.7812. Min Act: -0.0000

Data Index: 464456 (C4 (Web Text))

Max Activating Token Index: 334

Text #6

Max Range: 2.1404. Min Range: -2.1404

Max Act: 1.7870. Min Act: 0.0000

Data Index: 1012456 (C4 (Web Text))

Max Activating Token Index: 759

Text #7

Max Range: 2.1404. Min Range: -2.1404

Max Act: 1.8367. Min Act: -0.0000

Data Index: 588255 (C4 (Web Text))

Max Activating Token Index: 100

Text #8

Max Range: 2.1404. Min Range: -2.1404

Max Act: 1.6688. Min Act: 0.0000

Data Index: 956095 (C4 (Web Text))

Max Activating Token Index: 367

Text #9

Max Range: 2.1404. Min Range: -2.1404

Max Act: 1.5535. Min Act: -0.0000

Data Index: 1297265 (C4 (Web Text))

Max Activating Token Index: 493

Text #10

Max Range: 2.1404. Min Range: -2.1404

Max Act: 1.5547. Min Act: -0.0000

Data Index: 543544 (C4 (Web Text))

Max Activating Token Index: 289

Text #11

Max Range: 2.1404. Min Range: -2.1404

Max Act: 1.5504. Min Act: -0.0000

Data Index: 1116831 (C4 (Web Text))

Max Activating Token Index: 354

Text #12

Max Range: 2.1404. Min Range: -2.1404

Max Act: 1.6795. Min Act: -0.0000

Data Index: 244574 (C4 (Web Text))

Max Activating Token Index: 180

Text #13

Max Range: 2.1404. Min Range: -2.1404

Max Act: 1.5673. Min Act: -0.0000

Data Index: 1232883 (C4 (Web Text))

Max Activating Token Index: 422

Text #14

Max Range: 2.1404. Min Range: -2.1404

Max Act: 1.6469. Min Act: -0.0000

Data Index: 323369 (C4 (Web Text))

Max Activating Token Index: 562

Text #15

Max Range: 2.1404. Min Range: -2.1404

Max Act: 1.5214. Min Act: -0.0000

Data Index: 588754 (C4 (Web Text))

Max Activating Token Index: 441

Text #16

Max Range: 2.1404. Min Range: -2.1404

Max Act: 1.4246. Min Act: -0.0000

Data Index: 845648 (C4 (Web Text))

Max Activating Token Index: 742

Text #17

Max Range: 2.1404. Min Range: -2.1404

Max Act: 1.4997. Min Act: 0.0000

Data Index: 462565 (C4 (Web Text))

Max Activating Token Index: 426

Text #18

Max Range: 2.1404. Min Range: -2.1404

Max Act: 1.4920. Min Act: -0.0000

Data Index: 888503 (C4 (Web Text))

Max Activating Token Index: 114

Text #19

Max Range: 2.1404. Min Range: -2.1404

Max Act: 1.3906. Min Act: -0.0000

Data Index: 837633 (C4 (Web Text))

Max Activating Token Index: 197