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

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

Neuron 847 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: 3.5568. Min Range: -3.5568

Max Act: 3.5568. Min Act: -0.1700

Data Index: 274428 (C4 (Web Text))

Max Activating Token Index: 748

Text #1

Max Range: 3.5568. Min Range: -3.5568

Max Act: 3.5098. Min Act: -0.1700

Data Index: 1239783 (C4 (Web Text))

Max Activating Token Index: 1014

Text #2

Max Range: 3.5568. Min Range: -3.5568

Max Act: 3.4471. Min Act: -0.1700

Data Index: 798011 (C4 (Web Text))

Max Activating Token Index: 910

Text #3

Max Range: 3.5568. Min Range: -3.5568

Max Act: 3.4158. Min Act: -0.1700

Data Index: 61698 (C4 (Web Text))

Max Activating Token Index: 143

Text #4

Max Range: 3.5568. Min Range: -3.5568

Max Act: 3.4158. Min Act: -0.1700

Data Index: 469369 (C4 (Web Text))

Max Activating Token Index: 471

Text #5

Max Range: 3.5568. Min Range: -3.5568

Max Act: 3.4158. Min Act: -0.1700

Data Index: 506743 (C4 (Web Text))

Max Activating Token Index: 552

Text #6

Max Range: 3.5568. Min Range: -3.5568

Max Act: 3.4001. Min Act: -0.1700

Data Index: 412580 (C4 (Web Text))

Max Activating Token Index: 281

Text #7

Max Range: 3.5568. Min Range: -3.5568

Max Act: 3.4001. Min Act: -0.1700

Data Index: 563442 (C4 (Web Text))

Max Activating Token Index: 986

Text #8

Max Range: 3.5568. Min Range: -3.5568

Max Act: 3.3530. Min Act: -0.1700

Data Index: 851061 (C4 (Web Text))

Max Activating Token Index: 726

Text #9

Max Range: 3.5568. Min Range: -3.5568

Max Act: 3.3216. Min Act: -0.1700

Data Index: 815904 (C4 (Web Text))

Max Activating Token Index: 496

Text #10

Max Range: 3.5568. Min Range: -3.5568

Max Act: 3.3373. Min Act: -0.1700

Data Index: 776832 (C4 (Web Text))

Max Activating Token Index: 540

Text #11

Max Range: 3.5568. Min Range: -3.5568

Max Act: 3.3373. Min Act: -0.1700

Data Index: 966876 (C4 (Web Text))

Max Activating Token Index: 480

Text #12

Max Range: 3.5568. Min Range: -3.5568

Max Act: 3.3216. Min Act: -0.1700

Data Index: 1137077 (C4 (Web Text))

Max Activating Token Index: 504

Text #13

Max Range: 3.5568. Min Range: -3.5568

Max Act: 3.2902. Min Act: -0.1700

Data Index: 708196 (C4 (Web Text))

Max Activating Token Index: 478

Text #14

Max Range: 3.5568. Min Range: -3.5568

Max Act: 3.3059. Min Act: -0.1700

Data Index: 1317926 (C4 (Web Text))

Max Activating Token Index: 760

Text #15

Max Range: 3.5568. Min Range: -3.5568

Max Act: 3.3373. Min Act: -0.1700

Data Index: 615539 (C4 (Web Text))

Max Activating Token Index: 618

Text #16

Max Range: 3.5568. Min Range: -3.5568

Max Act: 3.3530. Min Act: -0.1700

Data Index: 714316 (C4 (Web Text))

Max Activating Token Index: 382

Text #17

Max Range: 3.5568. Min Range: -3.5568

Max Act: 3.2902. Min Act: -0.1700

Data Index: 1163681 (C4 (Web Text))

Max Activating Token Index: 219

Text #18

Max Range: 3.5568. Min Range: -3.5568

Max Act: 3.3216. Min Act: -0.1700

Data Index: 208661 (C4 (Web Text))

Max Activating Token Index: 695

Text #19

Max Range: 3.5568. Min Range: -3.5568

Max Act: 3.2902. Min Act: -0.1700

Data Index: 172369 (C4 (Web Text))

Max Activating Token Index: 36