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

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

Neuron 442 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: 1.6688. Min Range: -1.6688

Max Act: 1.6688. Min Act: -0.0002

Data Index: 1215771 (C4 (Web Text))

Max Activating Token Index: 201

Text #1

Max Range: 1.6688. Min Range: -1.6688

Max Act: 1.5321. Min Act: -0.0003

Data Index: 678982 (C4 (Web Text))

Max Activating Token Index: 715

Text #2

Max Range: 1.6688. Min Range: -1.6688

Max Act: 1.4627. Min Act: -0.0002

Data Index: 1015502 (C4 (Web Text))

Max Activating Token Index: 793

Text #3

Max Range: 1.6688. Min Range: -1.6688

Max Act: 1.3851. Min Act: -0.0002

Data Index: 285412 (C4 (Web Text))

Max Activating Token Index: 793

Text #4

Max Range: 1.6688. Min Range: -1.6688

Max Act: 1.3590. Min Act: -0.0003

Data Index: 1297124 (C4 (Web Text))

Max Activating Token Index: 755

Text #5

Max Range: 1.6688. Min Range: -1.6688

Max Act: 1.3034. Min Act: -0.0002

Data Index: 1128781 (C4 (Web Text))

Max Activating Token Index: 222

Text #6

Max Range: 1.6688. Min Range: -1.6688

Max Act: 1.2399. Min Act: -0.0003

Data Index: 686014 (C4 (Web Text))

Max Activating Token Index: 110

Text #7

Max Range: 1.6688. Min Range: -1.6688

Max Act: 1.2638. Min Act: -0.0002

Data Index: 1210442 (C4 (Web Text))

Max Activating Token Index: 792

Text #8

Max Range: 1.6688. Min Range: -1.6688

Max Act: 1.2128. Min Act: -0.0002

Data Index: 42095 (C4 (Web Text))

Max Activating Token Index: 18

Text #9

Max Range: 1.6688. Min Range: -1.6688

Max Act: 1.2024. Min Act: -0.0002

Data Index: 40752 (C4 (Web Text))

Max Activating Token Index: 863

Text #10

Max Range: 1.6688. Min Range: -1.6688

Max Act: 1.2117. Min Act: -0.0002

Data Index: 723763 (C4 (Web Text))

Max Activating Token Index: 170

Text #11

Max Range: 1.6688. Min Range: -1.6688

Max Act: 1.1850. Min Act: -0.0002

Data Index: 129654 (C4 (Web Text))

Max Activating Token Index: 236

Text #12

Max Range: 1.6688. Min Range: -1.6688

Max Act: 1.1726. Min Act: -0.0002

Data Index: 1000710 (C4 (Web Text))

Max Activating Token Index: 75

Text #13

Max Range: 1.6688. Min Range: -1.6688

Max Act: 1.1762. Min Act: -0.0002

Data Index: 712662 (C4 (Web Text))

Max Activating Token Index: 652

Text #14

Max Range: 1.6688. Min Range: -1.6688

Max Act: 1.1862. Min Act: -0.0003

Data Index: 812437 (C4 (Web Text))

Max Activating Token Index: 458

Text #15

Max Range: 1.6688. Min Range: -1.6688

Max Act: 1.1592. Min Act: -0.0002

Data Index: 18214 (C4 (Web Text))

Max Activating Token Index: 720

Text #16

Max Range: 1.6688. Min Range: -1.6688

Max Act: 1.1458. Min Act: -0.0002

Data Index: 298860 (C4 (Web Text))

Max Activating Token Index: 684

Text #17

Max Range: 1.6688. Min Range: -1.6688

Max Act: 1.1626. Min Act: -0.0002

Data Index: 1060113 (C4 (Web Text))

Max Activating Token Index: 911

Text #18

Max Range: 1.6688. Min Range: -1.6688

Max Act: 1.1125. Min Act: -0.0002

Data Index: 73219 (C4 (Web Text))

Max Activating Token Index: 263

Text #19

Max Range: 1.6688. Min Range: -1.6688

Max Act: 1.1113. Min Act: -0.0002

Data Index: 151716 (C4 (Web Text))

Max Activating Token Index: 286