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

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

Neuron 1237 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.6664. Min Range: -3.6664

Max Act: 3.6664. Min Act: -0.1700

Data Index: 852228 (C4 (Web Text))

Max Activating Token Index: 316

Text #1

Max Range: 3.6664. Min Range: -3.6664

Max Act: 3.5255. Min Act: -0.1700

Data Index: 910132 (C4 (Web Text))

Max Activating Token Index: 328

Text #2

Max Range: 3.6664. Min Range: -3.6664

Max Act: 3.5255. Min Act: -0.1700

Data Index: 750554 (C4 (Web Text))

Max Activating Token Index: 498

Text #3

Max Range: 3.6664. Min Range: -3.6664

Max Act: 3.5255. Min Act: -0.1700

Data Index: 550745 (C4 (Web Text))

Max Activating Token Index: 309

Text #4

Max Range: 3.6664. Min Range: -3.6664

Max Act: 3.4942. Min Act: -0.1700

Data Index: 1227895 (C4 (Web Text))

Max Activating Token Index: 694

Text #5

Max Range: 3.6664. Min Range: -3.6664

Max Act: 3.4471. Min Act: -0.1700

Data Index: 292538 (C4 (Web Text))

Max Activating Token Index: 768

Text #6

Max Range: 3.6664. Min Range: -3.6664

Max Act: 3.4785. Min Act: -0.1700

Data Index: 747074 (C4 (Web Text))

Max Activating Token Index: 507

Text #7

Max Range: 3.6664. Min Range: -3.6664

Max Act: 3.4471. Min Act: -0.1700

Data Index: 1010683 (C4 (Web Text))

Max Activating Token Index: 433

Text #8

Max Range: 3.6664. Min Range: -3.6664

Max Act: 3.4001. Min Act: -0.1700

Data Index: 576977 (C4 (Web Text))

Max Activating Token Index: 991

Text #9

Max Range: 3.6664. Min Range: -3.6664

Max Act: 3.3687. Min Act: -0.1700

Data Index: 969679 (C4 (Web Text))

Max Activating Token Index: 332

Text #10

Max Range: 3.6664. Min Range: -3.6664

Max Act: 3.4158. Min Act: -0.1700

Data Index: 218512 (C4 (Web Text))

Max Activating Token Index: 428

Text #11

Max Range: 3.6664. Min Range: -3.6664

Max Act: 3.3687. Min Act: -0.1700

Data Index: 1193520 (C4 (Web Text))

Max Activating Token Index: 113

Text #12

Max Range: 3.6664. Min Range: -3.6664

Max Act: 3.3530. Min Act: -0.1700

Data Index: 961302 (C4 (Web Text))

Max Activating Token Index: 503

Text #13

Max Range: 3.6664. Min Range: -3.6664

Max Act: 3.3530. Min Act: -0.1700

Data Index: 1350849 (C4 (Web Text))

Max Activating Token Index: 338

Text #14

Max Range: 3.6664. Min Range: -3.6664

Max Act: 3.3844. Min Act: -0.1700

Data Index: 444686 (C4 (Web Text))

Max Activating Token Index: 541

Text #15

Max Range: 3.6664. Min Range: -3.6664

Max Act: 3.3373. Min Act: -0.1700

Data Index: 665355 (C4 (Web Text))

Max Activating Token Index: 255

Text #16

Max Range: 3.6664. Min Range: -3.6664

Max Act: 3.3687. Min Act: -0.1700

Data Index: 953539 (C4 (Web Text))

Max Activating Token Index: 919

Text #17

Max Range: 3.6664. Min Range: -3.6664

Max Act: 3.2745. Min Act: -0.1700

Data Index: 149062 (C4 (Web Text))

Max Activating Token Index: 442

Text #18

Max Range: 3.6664. Min Range: -3.6664

Max Act: 3.3530. Min Act: -0.1700

Data Index: 795912 (C4 (Web Text))

Max Activating Token Index: 403

Text #19

Max Range: 3.6664. Min Range: -3.6664

Max Act: 3.3373. Min Act: -0.1700

Data Index: 979898 (C4 (Web Text))

Max Activating Token Index: 754