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

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

Neuron 4742 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Click the toggle to see the full text!

Text #0

Max Range: 2.1095. Min Range: -2.1095

Max Act: 2.1095. Min Act: -0.0002

Data Index: 1147548 (C4 (Web Text))

Max Activating Token Index: 609

Text #1

Max Range: 2.1095. Min Range: -2.1095

Max Act: 1.8839. Min Act: -0.0002

Data Index: 1109661 (C4 (Web Text))

Max Activating Token Index: 438

Text #2

Max Range: 2.1095. Min Range: -2.1095

Max Act: 1.8246. Min Act: -0.0002

Data Index: 436950 (C4 (Web Text))

Max Activating Token Index: 582

Text #3

Max Range: 2.1095. Min Range: -2.1095

Max Act: 1.7000. Min Act: -0.0002

Data Index: 1009736 (C4 (Web Text))

Max Activating Token Index: 526

Text #4

Max Range: 2.1095. Min Range: -2.1095

Max Act: 1.6322. Min Act: -0.0002

Data Index: 94075 (C4 (Web Text))

Max Activating Token Index: 963

Text #5

Max Range: 2.1095. Min Range: -2.1095

Max Act: 1.5839. Min Act: -0.0003

Data Index: 126902 (C4 (Web Text))

Max Activating Token Index: 702

Text #6

Max Range: 2.1095. Min Range: -2.1095

Max Act: 1.5262. Min Act: -0.0002

Data Index: 625430 (C4 (Web Text))

Max Activating Token Index: 576

Text #7

Max Range: 2.1095. Min Range: -2.1095

Max Act: 1.4452. Min Act: -0.0002

Data Index: 844789 (C4 (Web Text))

Max Activating Token Index: 684

Text #8

Max Range: 2.1095. Min Range: -2.1095

Max Act: 1.4332. Min Act: -0.0002

Data Index: 802602 (C4 (Web Text))

Max Activating Token Index: 781

Text #9

Max Range: 2.1095. Min Range: -2.1095

Max Act: 1.3933. Min Act: -0.0002

Data Index: 1135465 (C4 (Web Text))

Max Activating Token Index: 711

Text #10

Max Range: 2.1095. Min Range: -2.1095

Max Act: 1.4134. Min Act: -0.0002

Data Index: 1230599 (C4 (Web Text))

Max Activating Token Index: 479

Text #11

Max Range: 2.1095. Min Range: -2.1095

Max Act: 1.4029. Min Act: -0.0002

Data Index: 65147 (C4 (Web Text))

Max Activating Token Index: 676

Text #12

Max Range: 2.1095. Min Range: -2.1095

Max Act: 1.3802. Min Act: -0.0002

Data Index: 125610 (C4 (Web Text))

Max Activating Token Index: 620

Text #13

Max Range: 2.1095. Min Range: -2.1095

Max Act: 1.3842. Min Act: -0.0002

Data Index: 875065 (C4 (Web Text))

Max Activating Token Index: 608

Text #14

Max Range: 2.1095. Min Range: -2.1095

Max Act: 1.4042. Min Act: -0.0002

Data Index: 669239 (C4 (Web Text))

Max Activating Token Index: 594

Text #15

Max Range: 2.1095. Min Range: -2.1095

Max Act: 1.3928. Min Act: -0.0003

Data Index: 619779 (C4 (Web Text))

Max Activating Token Index: 692

Text #16

Max Range: 2.1095. Min Range: -2.1095

Max Act: 1.3797. Min Act: -0.0002

Data Index: 641112 (C4 (Web Text))

Max Activating Token Index: 716

Text #17

Max Range: 2.1095. Min Range: -2.1095

Max Act: 1.3676. Min Act: -0.0002

Data Index: 1073768 (C4 (Web Text))

Max Activating Token Index: 660

Text #18

Max Range: 2.1095. Min Range: -2.1095

Max Act: 1.3870. Min Act: -0.0002

Data Index: 74243 (C4 (Web Text))

Max Activating Token Index: 660

Text #19

Max Range: 2.1095. Min Range: -2.1095

Max Act: 1.3923. Min Act: -0.0002

Data Index: 291034 (C4 (Web Text))

Max Activating Token Index: 747