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

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

Neuron 361 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.1938. Min Range: -3.1938

Max Act: 3.1938. Min Act: -0.1700

Data Index: 138279 (C4 (Web Text))

Max Activating Token Index: 811

Text #1

Max Range: 3.1938. Min Range: -3.1938

Max Act: 3.0993. Min Act: -0.1700

Data Index: 1136589 (C4 (Web Text))

Max Activating Token Index: 1019

Text #2

Max Range: 3.1938. Min Range: -3.1938

Max Act: 2.9096. Min Act: -0.1700

Data Index: 1520580 (Python Code)

Max Activating Token Index: 20

Text #3

Max Range: 3.1938. Min Range: -3.1938

Max Act: 2.7345. Min Act: -0.1700

Data Index: 241777 (C4 (Web Text))

Max Activating Token Index: 783

Text #4

Max Range: 3.1938. Min Range: -3.1938

Max Act: 2.6866. Min Act: -0.1700

Data Index: 696831 (C4 (Web Text))

Max Activating Token Index: 461

Text #5

Max Range: 3.1938. Min Range: -3.1938

Max Act: 2.6866. Min Act: -0.1700

Data Index: 138092 (C4 (Web Text))

Max Activating Token Index: 334

Text #6

Max Range: 3.1938. Min Range: -3.1938

Max Act: 2.6705. Min Act: -0.1700

Data Index: 877476 (C4 (Web Text))

Max Activating Token Index: 778

Text #7

Max Range: 3.1938. Min Range: -3.1938

Max Act: 2.6385. Min Act: -0.1700

Data Index: 459528 (C4 (Web Text))

Max Activating Token Index: 306

Text #8

Max Range: 3.1938. Min Range: -3.1938

Max Act: 2.6224. Min Act: -0.1700

Data Index: 824295 (C4 (Web Text))

Max Activating Token Index: 617

Text #9

Max Range: 3.1938. Min Range: -3.1938

Max Act: 2.5741. Min Act: -0.1700

Data Index: 732867 (C4 (Web Text))

Max Activating Token Index: 665

Text #10

Max Range: 3.1938. Min Range: -3.1938

Max Act: 2.5741. Min Act: -0.1700

Data Index: 807986 (C4 (Web Text))

Max Activating Token Index: 403

Text #11

Max Range: 3.1938. Min Range: -3.1938

Max Act: 2.6063. Min Act: -0.1700

Data Index: 1355269 (C4 (Web Text))

Max Activating Token Index: 603

Text #12

Max Range: 3.1938. Min Range: -3.1938

Max Act: 2.5902. Min Act: -0.1700

Data Index: 494358 (C4 (Web Text))

Max Activating Token Index: 2

Text #13

Max Range: 3.1938. Min Range: -3.1938

Max Act: 2.5741. Min Act: -0.1700

Data Index: 18369 (C4 (Web Text))

Max Activating Token Index: 755

Text #14

Max Range: 3.1938. Min Range: -3.1938

Max Act: 2.5741. Min Act: -0.1700

Data Index: 732766 (C4 (Web Text))

Max Activating Token Index: 646

Text #15

Max Range: 3.1938. Min Range: -3.1938

Max Act: 2.5580. Min Act: -0.1700

Data Index: 425366 (C4 (Web Text))

Max Activating Token Index: 589

Text #16

Max Range: 3.1938. Min Range: -3.1938

Max Act: 2.5741. Min Act: -0.1700

Data Index: 991523 (C4 (Web Text))

Max Activating Token Index: 121

Text #17

Max Range: 3.1938. Min Range: -3.1938

Max Act: 2.5257. Min Act: -0.1700

Data Index: 245685 (C4 (Web Text))

Max Activating Token Index: 558

Text #18

Max Range: 3.1938. Min Range: -3.1938

Max Act: 2.5580. Min Act: -0.1700

Data Index: 796306 (C4 (Web Text))

Max Activating Token Index: 103

Text #19

Max Range: 3.1938. Min Range: -3.1938

Max Act: 2.5257. Min Act: -0.1700

Data Index: 603740 (C4 (Web Text))

Max Activating Token Index: 126