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

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

Neuron 1766 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: 3.5426. Min Range: -3.5426

Max Act: 3.5426. Min Act: -0.1700

Data Index: 120224 (C4 (Web Text))

Max Activating Token Index: 967

Text #1

Max Range: 3.5426. Min Range: -3.5426

Max Act: 3.5113. Min Act: -0.1700

Data Index: 106193 (C4 (Web Text))

Max Activating Token Index: 892

Text #2

Max Range: 3.5426. Min Range: -3.5426

Max Act: 3.5270. Min Act: -0.1700

Data Index: 1300399 (C4 (Web Text))

Max Activating Token Index: 606

Text #3

Max Range: 3.5426. Min Range: -3.5426

Max Act: 3.5270. Min Act: -0.1700

Data Index: 1199381 (C4 (Web Text))

Max Activating Token Index: 888

Text #4

Max Range: 3.5426. Min Range: -3.5426

Max Act: 3.4800. Min Act: -0.1700

Data Index: 884494 (C4 (Web Text))

Max Activating Token Index: 1019

Text #5

Max Range: 3.5426. Min Range: -3.5426

Max Act: 3.4956. Min Act: -0.1700

Data Index: 721199 (C4 (Web Text))

Max Activating Token Index: 887

Text #6

Max Range: 3.5426. Min Range: -3.5426

Max Act: 3.4486. Min Act: -0.1700

Data Index: 537777 (C4 (Web Text))

Max Activating Token Index: 570

Text #7

Max Range: 3.5426. Min Range: -3.5426

Max Act: 3.4643. Min Act: -0.1700

Data Index: 215896 (C4 (Web Text))

Max Activating Token Index: 806

Text #8

Max Range: 3.5426. Min Range: -3.5426

Max Act: 3.4643. Min Act: -0.1700

Data Index: 373164 (C4 (Web Text))

Max Activating Token Index: 609

Text #9

Max Range: 3.5426. Min Range: -3.5426

Max Act: 3.4016. Min Act: -0.1700

Data Index: 722637 (C4 (Web Text))

Max Activating Token Index: 916

Text #10

Max Range: 3.5426. Min Range: -3.5426

Max Act: 3.4016. Min Act: -0.1700

Data Index: 162354 (C4 (Web Text))

Max Activating Token Index: 928

Text #11

Max Range: 3.5426. Min Range: -3.5426

Max Act: 3.3702. Min Act: -0.1700

Data Index: 563363 (C4 (Web Text))

Max Activating Token Index: 501

Text #12

Max Range: 3.5426. Min Range: -3.5426

Max Act: 3.3702. Min Act: -0.1700

Data Index: 722475 (C4 (Web Text))

Max Activating Token Index: 657

Text #13

Max Range: 3.5426. Min Range: -3.5426

Max Act: 3.3859. Min Act: -0.1700

Data Index: 625927 (C4 (Web Text))

Max Activating Token Index: 115

Text #14

Max Range: 3.5426. Min Range: -3.5426

Max Act: 3.3859. Min Act: -0.1700

Data Index: 885645 (C4 (Web Text))

Max Activating Token Index: 591

Text #15

Max Range: 3.5426. Min Range: -3.5426

Max Act: 3.3702. Min Act: -0.1700

Data Index: 331354 (C4 (Web Text))

Max Activating Token Index: 34

Text #16

Max Range: 3.5426. Min Range: -3.5426

Max Act: 3.3231. Min Act: -0.1700

Data Index: 626410 (C4 (Web Text))

Max Activating Token Index: 73

Text #17

Max Range: 3.5426. Min Range: -3.5426

Max Act: 3.2446. Min Act: -0.1700

Data Index: 252301 (C4 (Web Text))

Max Activating Token Index: 666

Text #18

Max Range: 3.5426. Min Range: -3.5426

Max Act: 3.1974. Min Act: -0.1700

Data Index: 1269713 (C4 (Web Text))

Max Activating Token Index: 66

Text #19

Max Range: 3.5426. Min Range: -3.5426

Max Act: 3.1817. Min Act: -0.1700

Data Index: 1250610 (C4 (Web Text))

Max Activating Token Index: 314