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

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

Neuron 1357 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: 0.0738. Min Range: -0.0738

Max Act: 0.0738. Min Act: -0.0002

Data Index: 26616 (C4 (Web Text))

Max Activating Token Index: 271

Text #1

Max Range: 0.0738. Min Range: -0.0738

Max Act: 0.0700. Min Act: -0.0002

Data Index: 1101817 (C4 (Web Text))

Max Activating Token Index: 107

Text #2

Max Range: 0.0738. Min Range: -0.0738

Max Act: 0.0693. Min Act: -0.0002

Data Index: 966572 (C4 (Web Text))

Max Activating Token Index: 83

Text #3

Max Range: 0.0738. Min Range: -0.0738

Max Act: 0.0674. Min Act: -0.0002

Data Index: 251534 (C4 (Web Text))

Max Activating Token Index: 114

Text #4

Max Range: 0.0738. Min Range: -0.0738

Max Act: 0.0673. Min Act: -0.0002

Data Index: 490569 (C4 (Web Text))

Max Activating Token Index: 786

Text #5

Max Range: 0.0738. Min Range: -0.0738

Max Act: 0.0675. Min Act: -0.0002

Data Index: 325501 (C4 (Web Text))

Max Activating Token Index: 201

Text #6

Max Range: 0.0738. Min Range: -0.0738

Max Act: 0.0660. Min Act: -0.0002

Data Index: 688223 (C4 (Web Text))

Max Activating Token Index: 809

Text #7

Max Range: 0.0738. Min Range: -0.0738

Max Act: 0.0672. Min Act: -0.0002

Data Index: 664591 (C4 (Web Text))

Max Activating Token Index: 302

Text #8

Max Range: 0.0738. Min Range: -0.0738

Max Act: 0.0658. Min Act: -0.0002

Data Index: 132505 (C4 (Web Text))

Max Activating Token Index: 125

Text #9

Max Range: 0.0738. Min Range: -0.0738

Max Act: 0.0670. Min Act: -0.0002

Data Index: 225239 (C4 (Web Text))

Max Activating Token Index: 82

Text #10

Max Range: 0.0738. Min Range: -0.0738

Max Act: 0.0659. Min Act: -0.0002

Data Index: 1046468 (C4 (Web Text))

Max Activating Token Index: 47

Text #11

Max Range: 0.0738. Min Range: -0.0738

Max Act: 0.0659. Min Act: -0.0002

Data Index: 610281 (C4 (Web Text))

Max Activating Token Index: 137

Text #12

Max Range: 0.0738. Min Range: -0.0738

Max Act: 0.0650. Min Act: -0.0002

Data Index: 619680 (C4 (Web Text))

Max Activating Token Index: 40

Text #13

Max Range: 0.0738. Min Range: -0.0738

Max Act: 0.0652. Min Act: -0.0002

Data Index: 1063395 (C4 (Web Text))

Max Activating Token Index: 907

Text #14

Max Range: 0.0738. Min Range: -0.0738

Max Act: 0.0640. Min Act: -0.0002

Data Index: 625990 (C4 (Web Text))

Max Activating Token Index: 1014

Text #15

Max Range: 0.0738. Min Range: -0.0738

Max Act: 0.0636. Min Act: -0.0002

Data Index: 993823 (C4 (Web Text))

Max Activating Token Index: 62

Text #16

Max Range: 0.0738. Min Range: -0.0738

Max Act: 0.0628. Min Act: -0.0002

Data Index: 279526 (C4 (Web Text))

Max Activating Token Index: 92

Text #17

Max Range: 0.0738. Min Range: -0.0738

Max Act: 0.0637. Min Act: -0.0002

Data Index: 327004 (C4 (Web Text))

Max Activating Token Index: 99

Text #18

Max Range: 0.0738. Min Range: -0.0738

Max Act: 0.0657. Min Act: -0.0002

Data Index: 134057 (C4 (Web Text))

Max Activating Token Index: 342

Text #19

Max Range: 0.0738. Min Range: -0.0738

Max Act: 0.0639. Min Act: -0.0002

Data Index: 1078721 (C4 (Web Text))

Max Activating Token Index: 23