Model: GELU Model: 1 Layers, 2048 Neurons per Layer

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

Neuron 1801 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Hooked Transformer Loading: HookedTransformer.from_pretrained('gelu-1l')

Click the toggle to see the full text!

Text #0

Max Range: 4.9444. Min Range: -4.9444

Max Act: 4.9444. Min Act: -0.1700

Data Index: 204311 (C4 (Web Text))

Max Activating Token Index: 294

Text #1

Max Range: 4.9444. Min Range: -4.9444

Max Act: 4.7033. Min Act: -0.1700

Data Index: 763908 (C4 (Web Text))

Max Activating Token Index: 705

Text #2

Max Range: 4.9444. Min Range: -4.9444

Max Act: 4.6242. Min Act: -0.1700

Data Index: 1089489 (C4 (Web Text))

Max Activating Token Index: 176

Text #3

Max Range: 4.9444. Min Range: -4.9444

Max Act: 4.5458. Min Act: -0.1700

Data Index: 642612 (C4 (Web Text))

Max Activating Token Index: 272

Text #4

Max Range: 4.9444. Min Range: -4.9444

Max Act: 4.5039. Min Act: -0.1700

Data Index: 959166 (C4 (Web Text))

Max Activating Token Index: 819

Text #5

Max Range: 4.9444. Min Range: -4.9444

Max Act: 4.5256. Min Act: -0.1700

Data Index: 433185 (C4 (Web Text))

Max Activating Token Index: 447

Text #6

Max Range: 4.9444. Min Range: -4.9444

Max Act: 4.4753. Min Act: -0.1700

Data Index: 263689 (C4 (Web Text))

Max Activating Token Index: 277

Text #7

Max Range: 4.9444. Min Range: -4.9444

Max Act: 4.4809. Min Act: -0.1700

Data Index: 721504 (C4 (Web Text))

Max Activating Token Index: 450

Text #8

Max Range: 4.9444. Min Range: -4.9444

Max Act: 4.4708. Min Act: -0.1700

Data Index: 30017 (C4 (Web Text))

Max Activating Token Index: 585

Text #9

Max Range: 4.9444. Min Range: -4.9444

Max Act: 4.4714. Min Act: -0.1700

Data Index: 354141 (C4 (Web Text))

Max Activating Token Index: 773

Text #10

Max Range: 4.9444. Min Range: -4.9444

Max Act: 4.4711. Min Act: -0.1700

Data Index: 646993 (C4 (Web Text))

Max Activating Token Index: 981

Text #11

Max Range: 4.9444. Min Range: -4.9444

Max Act: 4.4645. Min Act: -0.1700

Data Index: 1071556 (C4 (Web Text))

Max Activating Token Index: 197

Text #12

Max Range: 4.9444. Min Range: -4.9444

Max Act: 4.4509. Min Act: -0.1700

Data Index: 1148702 (C4 (Web Text))

Max Activating Token Index: 430

Text #13

Max Range: 4.9444. Min Range: -4.9444

Max Act: 4.4745. Min Act: -0.1700

Data Index: 1219214 (C4 (Web Text))

Max Activating Token Index: 649

Text #14

Max Range: 4.9444. Min Range: -4.9444

Max Act: 4.4597. Min Act: -0.1700

Data Index: 869264 (C4 (Web Text))

Max Activating Token Index: 879

Text #15

Max Range: 4.9444. Min Range: -4.9444

Max Act: 4.4474. Min Act: -0.1700

Data Index: 2556 (C4 (Web Text))

Max Activating Token Index: 960

Text #16

Max Range: 4.9444. Min Range: -4.9444

Max Act: 4.4387. Min Act: -0.1700

Data Index: 1277910 (C4 (Web Text))

Max Activating Token Index: 590

Text #17

Max Range: 4.9444. Min Range: -4.9444

Max Act: 4.4639. Min Act: -0.1700

Data Index: 375685 (C4 (Web Text))

Max Activating Token Index: 460

Text #18

Max Range: 4.9444. Min Range: -4.9444

Max Act: 4.4015. Min Act: -0.1700

Data Index: 798284 (C4 (Web Text))

Max Activating Token Index: 715

Text #19

Max Range: 4.9444. Min Range: -4.9444

Max Act: 4.4539. Min Act: -0.1700

Data Index: 441410 (C4 (Web Text))

Max Activating Token Index: 164