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

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

Neuron 2927 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: 4.7656. Min Range: -4.7656

Max Act: 4.7656. Min Act: -0.0003

Data Index: 1052083 (C4 (Web Text))

Max Activating Token Index: 450

Text #1

Max Range: 4.7656. Min Range: -4.7656

Max Act: 4.6253. Min Act: -0.0002

Data Index: 165098 (C4 (Web Text))

Max Activating Token Index: 737

Text #2

Max Range: 4.7656. Min Range: -4.7656

Max Act: 4.5551. Min Act: -0.0002

Data Index: 648800 (C4 (Web Text))

Max Activating Token Index: 631

Text #3

Max Range: 4.7656. Min Range: -4.7656

Max Act: 4.3423. Min Act: -0.0002

Data Index: 1310089 (C4 (Web Text))

Max Activating Token Index: 188

Text #4

Max Range: 4.7656. Min Range: -4.7656

Max Act: 4.3665. Min Act: -0.0002

Data Index: 1071219 (C4 (Web Text))

Max Activating Token Index: 342

Text #5

Max Range: 4.7656. Min Range: -4.7656

Max Act: 4.3046. Min Act: -0.0002

Data Index: 834099 (C4 (Web Text))

Max Activating Token Index: 676

Text #6

Max Range: 4.7656. Min Range: -4.7656

Max Act: 4.2786. Min Act: -0.0002

Data Index: 377572 (C4 (Web Text))

Max Activating Token Index: 288

Text #7

Max Range: 4.7656. Min Range: -4.7656

Max Act: 4.1025. Min Act: -0.0002

Data Index: 408587 (C4 (Web Text))

Max Activating Token Index: 947

Text #8

Max Range: 4.7656. Min Range: -4.7656

Max Act: 4.1256. Min Act: -0.0002

Data Index: 770249 (C4 (Web Text))

Max Activating Token Index: 251

Text #9

Max Range: 4.7656. Min Range: -4.7656

Max Act: 4.0590. Min Act: -0.0002

Data Index: 322905 (C4 (Web Text))

Max Activating Token Index: 193

Text #10

Max Range: 4.7656. Min Range: -4.7656

Max Act: 4.0404. Min Act: -0.0002

Data Index: 1039341 (C4 (Web Text))

Max Activating Token Index: 512

Text #11

Max Range: 4.7656. Min Range: -4.7656

Max Act: 4.0570. Min Act: -0.0002

Data Index: 619003 (C4 (Web Text))

Max Activating Token Index: 805

Text #12

Max Range: 4.7656. Min Range: -4.7656

Max Act: 4.0101. Min Act: -0.0002

Data Index: 1024725 (C4 (Web Text))

Max Activating Token Index: 294

Text #13

Max Range: 4.7656. Min Range: -4.7656

Max Act: 3.9459. Min Act: -0.0002

Data Index: 922776 (C4 (Web Text))

Max Activating Token Index: 34

Text #14

Max Range: 4.7656. Min Range: -4.7656

Max Act: 3.9712. Min Act: -0.0002

Data Index: 155605 (C4 (Web Text))

Max Activating Token Index: 783

Text #15

Max Range: 4.7656. Min Range: -4.7656

Max Act: 3.8876. Min Act: -0.0002

Data Index: 139337 (C4 (Web Text))

Max Activating Token Index: 354

Text #16

Max Range: 4.7656. Min Range: -4.7656

Max Act: 3.8760. Min Act: -0.0003

Data Index: 628300 (C4 (Web Text))

Max Activating Token Index: 459

Text #17

Max Range: 4.7656. Min Range: -4.7656

Max Act: 3.8583. Min Act: -0.0002

Data Index: 561617 (C4 (Web Text))

Max Activating Token Index: 387

Text #18

Max Range: 4.7656. Min Range: -4.7656

Max Act: 3.7329. Min Act: -0.0002

Data Index: 1025121 (C4 (Web Text))

Max Activating Token Index: 29

Text #19

Max Range: 4.7656. Min Range: -4.7656

Max Act: 3.7144. Min Act: -0.0002

Data Index: 1350278 (C4 (Web Text))

Max Activating Token Index: 221