Model: GELU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 578 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')

Text #0

Max Range: 3.5573. Min Range: -3.5573

Max Act: 3.5573. Min Act: -0.1700

Data Index: 344967 (C4 (Web Text))

Max Activating Token Index: 731

Text #1

Max Range: 3.5573. Min Range: -3.5573

Max Act: 3.5416. Min Act: -0.1700

Data Index: 495203 (C4 (Web Text))

Max Activating Token Index: 106

Text #2

Max Range: 3.5573. Min Range: -3.5573

Max Act: 3.4790. Min Act: -0.1700

Data Index: 590572 (C4 (Web Text))

Max Activating Token Index: 352

Text #3

Max Range: 3.5573. Min Range: -3.5573

Max Act: 3.4633. Min Act: -0.1700

Data Index: 237623 (C4 (Web Text))

Max Activating Token Index: 110

Text #4

Max Range: 3.5573. Min Range: -3.5573

Max Act: 3.4006. Min Act: -0.1700

Data Index: 930158 (C4 (Web Text))

Max Activating Token Index: 48

Text #5

Max Range: 3.5573. Min Range: -3.5573

Max Act: 3.3378. Min Act: -0.1700

Data Index: 717771 (C4 (Web Text))

Max Activating Token Index: 852

Text #6

Max Range: 3.5573. Min Range: -3.5573

Max Act: 3.3849. Min Act: -0.1700

Data Index: 390354 (C4 (Web Text))

Max Activating Token Index: 59

Text #7

Max Range: 3.5573. Min Range: -3.5573

Max Act: 3.3692. Min Act: -0.1700

Data Index: 1014895 (C4 (Web Text))

Max Activating Token Index: 749

Text #8

Max Range: 3.5573. Min Range: -3.5573

Max Act: 3.3692. Min Act: -0.1700

Data Index: 972203 (C4 (Web Text))

Max Activating Token Index: 690

Text #9

Max Range: 3.5573. Min Range: -3.5573

Max Act: 3.3535. Min Act: -0.1700

Data Index: 490643 (C4 (Web Text))

Max Activating Token Index: 594

Text #10

Max Range: 3.5573. Min Range: -3.5573

Max Act: 3.3378. Min Act: -0.1700

Data Index: 264182 (C4 (Web Text))

Max Activating Token Index: 412

Text #11

Max Range: 3.5573. Min Range: -3.5573

Max Act: 3.3535. Min Act: -0.1700

Data Index: 1209353 (C4 (Web Text))

Max Activating Token Index: 680

Text #12

Max Range: 3.5573. Min Range: -3.5573

Max Act: 3.3535. Min Act: -0.1700

Data Index: 448946 (C4 (Web Text))

Max Activating Token Index: 112

Text #13

Max Range: 3.5573. Min Range: -3.5573

Max Act: 3.3535. Min Act: -0.1700

Data Index: 749109 (C4 (Web Text))

Max Activating Token Index: 581

Text #14

Max Range: 3.5573. Min Range: -3.5573

Max Act: 3.3064. Min Act: -0.1700

Data Index: 448032 (C4 (Web Text))

Max Activating Token Index: 489

Text #15

Max Range: 3.5573. Min Range: -3.5573

Max Act: 3.3221. Min Act: -0.1700

Data Index: 529229 (C4 (Web Text))

Max Activating Token Index: 784

Text #16

Max Range: 3.5573. Min Range: -3.5573

Max Act: 3.3535. Min Act: -0.1700

Data Index: 410380 (C4 (Web Text))

Max Activating Token Index: 306

Text #17

Max Range: 3.5573. Min Range: -3.5573

Max Act: 3.2750. Min Act: -0.1700

Data Index: 501594 (C4 (Web Text))

Max Activating Token Index: 364

Text #18

Max Range: 3.5573. Min Range: -3.5573

Max Act: 3.3064. Min Act: -0.1700

Data Index: 1050601 (C4 (Web Text))

Max Activating Token Index: 76

Text #19

Max Range: 3.5573. Min Range: -3.5573

Max Act: 3.3064. Min Act: -0.1699

Data Index: 443142 (C4 (Web Text))

Max Activating Token Index: 817