Model: GELU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 330 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-3l')

Text #0

Max Range: 3.6489. Min Range: -3.6489

Max Act: 3.6489. Min Act: -0.1700

Data Index: 167792 (C4 (Web Text))

Max Activating Token Index: 338

Text #1

Max Range: 3.6489. Min Range: -3.6489

Max Act: 3.5550. Min Act: -0.1700

Data Index: 405735 (C4 (Web Text))

Max Activating Token Index: 573

Text #2

Max Range: 3.6489. Min Range: -3.6489

Max Act: 3.5550. Min Act: -0.1700

Data Index: 392498 (C4 (Web Text))

Max Activating Token Index: 881

Text #3

Max Range: 3.6489. Min Range: -3.6489

Max Act: 3.5550. Min Act: -0.1700

Data Index: 367919 (C4 (Web Text))

Max Activating Token Index: 368

Text #4

Max Range: 3.6489. Min Range: -3.6489

Max Act: 3.5706. Min Act: -0.1700

Data Index: 844186 (C4 (Web Text))

Max Activating Token Index: 317

Text #5

Max Range: 3.6489. Min Range: -3.6489

Max Act: 3.5550. Min Act: -0.1700

Data Index: 839431 (C4 (Web Text))

Max Activating Token Index: 160

Text #6

Max Range: 3.6489. Min Range: -3.6489

Max Act: 3.5706. Min Act: -0.1700

Data Index: 487544 (C4 (Web Text))

Max Activating Token Index: 768

Text #7

Max Range: 3.6489. Min Range: -3.6489

Max Act: 3.5393. Min Act: -0.1700

Data Index: 171198 (C4 (Web Text))

Max Activating Token Index: 417

Text #8

Max Range: 3.6489. Min Range: -3.6489

Max Act: 3.5236. Min Act: -0.1700

Data Index: 803486 (C4 (Web Text))

Max Activating Token Index: 969

Text #9

Max Range: 3.6489. Min Range: -3.6489

Max Act: 3.4766. Min Act: -0.1700

Data Index: 752349 (C4 (Web Text))

Max Activating Token Index: 128

Text #10

Max Range: 3.6489. Min Range: -3.6489

Max Act: 3.5080. Min Act: -0.1700

Data Index: 1275746 (C4 (Web Text))

Max Activating Token Index: 1009

Text #11

Max Range: 3.6489. Min Range: -3.6489

Max Act: 3.5080. Min Act: -0.1700

Data Index: 998287 (C4 (Web Text))

Max Activating Token Index: 147

Text #12

Max Range: 3.6489. Min Range: -3.6489

Max Act: 3.4766. Min Act: -0.1700

Data Index: 500191 (C4 (Web Text))

Max Activating Token Index: 637

Text #13

Max Range: 3.6489. Min Range: -3.6489

Max Act: 3.4923. Min Act: -0.1700

Data Index: 1070676 (C4 (Web Text))

Max Activating Token Index: 331

Text #14

Max Range: 3.6489. Min Range: -3.6489

Max Act: 3.4609. Min Act: -0.1699

Data Index: 387268 (C4 (Web Text))

Max Activating Token Index: 703

Text #15

Max Range: 3.6489. Min Range: -3.6489

Max Act: 3.4609. Min Act: -0.1700

Data Index: 103719 (C4 (Web Text))

Max Activating Token Index: 420

Text #16

Max Range: 3.6489. Min Range: -3.6489

Max Act: 3.4609. Min Act: -0.1700

Data Index: 692227 (C4 (Web Text))

Max Activating Token Index: 102

Text #17

Max Range: 3.6489. Min Range: -3.6489

Max Act: 3.4609. Min Act: -0.1700

Data Index: 1274479 (C4 (Web Text))

Max Activating Token Index: 293

Text #18

Max Range: 3.6489. Min Range: -3.6489

Max Act: 3.4766. Min Act: -0.1700

Data Index: 1165931 (C4 (Web Text))

Max Activating Token Index: 707

Text #19

Max Range: 3.6489. Min Range: -3.6489

Max Act: 3.4766. Min Act: -0.1700

Data Index: 463516 (C4 (Web Text))

Max Activating Token Index: 783