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

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

Neuron 26 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: 3.8566. Min Range: -3.8566

Max Act: 3.8566. Min Act: -0.1700

Data Index: 566289 (C4 (Web Text))

Max Activating Token Index: 861

Text #1

Max Range: 3.8566. Min Range: -3.8566

Max Act: 3.8566. Min Act: -0.1700

Data Index: 950392 (C4 (Web Text))

Max Activating Token Index: 668

Text #2

Max Range: 3.8566. Min Range: -3.8566

Max Act: 3.8566. Min Act: -0.1700

Data Index: 312135 (C4 (Web Text))

Max Activating Token Index: 790

Text #3

Max Range: 3.8566. Min Range: -3.8566

Max Act: 3.7941. Min Act: -0.1700

Data Index: 672212 (C4 (Web Text))

Max Activating Token Index: 568

Text #4

Max Range: 3.8566. Min Range: -3.8566

Max Act: 3.8253. Min Act: -0.1700

Data Index: 699977 (C4 (Web Text))

Max Activating Token Index: 861

Text #5

Max Range: 3.8566. Min Range: -3.8566

Max Act: 3.8253. Min Act: -0.1700

Data Index: 1078422 (C4 (Web Text))

Max Activating Token Index: 483

Text #6

Max Range: 3.8566. Min Range: -3.8566

Max Act: 3.7941. Min Act: -0.1700

Data Index: 729694 (C4 (Web Text))

Max Activating Token Index: 566

Text #7

Max Range: 3.8566. Min Range: -3.8566

Max Act: 3.7941. Min Act: -0.1700

Data Index: 1032461 (C4 (Web Text))

Max Activating Token Index: 787

Text #8

Max Range: 3.8566. Min Range: -3.8566

Max Act: 3.7941. Min Act: -0.1700

Data Index: 358741 (C4 (Web Text))

Max Activating Token Index: 712

Text #9

Max Range: 3.8566. Min Range: -3.8566

Max Act: 3.7628. Min Act: -0.1700

Data Index: 384814 (C4 (Web Text))

Max Activating Token Index: 861

Text #10

Max Range: 3.8566. Min Range: -3.8566

Max Act: 3.7941. Min Act: -0.1700

Data Index: 24260 (C4 (Web Text))

Max Activating Token Index: 855

Text #11

Max Range: 3.8566. Min Range: -3.8566

Max Act: 3.7941. Min Act: -0.1700

Data Index: 151696 (C4 (Web Text))

Max Activating Token Index: 597

Text #12

Max Range: 3.8566. Min Range: -3.8566

Max Act: 3.7941. Min Act: -0.1700

Data Index: 1110448 (C4 (Web Text))

Max Activating Token Index: 828

Text #13

Max Range: 3.8566. Min Range: -3.8566

Max Act: 3.7941. Min Act: -0.1700

Data Index: 949623 (C4 (Web Text))

Max Activating Token Index: 911

Text #14

Max Range: 3.8566. Min Range: -3.8566

Max Act: 3.7941. Min Act: -0.1700

Data Index: 1158227 (C4 (Web Text))

Max Activating Token Index: 711

Text #15

Max Range: 3.8566. Min Range: -3.8566

Max Act: 3.7628. Min Act: -0.1700

Data Index: 323608 (C4 (Web Text))

Max Activating Token Index: 772

Text #16

Max Range: 3.8566. Min Range: -3.8566

Max Act: 3.7628. Min Act: -0.1700

Data Index: 417968 (C4 (Web Text))

Max Activating Token Index: 507

Text #17

Max Range: 3.8566. Min Range: -3.8566

Max Act: 3.7628. Min Act: -0.1700

Data Index: 905367 (C4 (Web Text))

Max Activating Token Index: 721

Text #18

Max Range: 3.8566. Min Range: -3.8566

Max Act: 3.7315. Min Act: -0.1700

Data Index: 225059 (C4 (Web Text))

Max Activating Token Index: 789

Text #19

Max Range: 3.8566. Min Range: -3.8566

Max Act: 3.7628. Min Act: -0.1700

Data Index: 929952 (C4 (Web Text))

Max Activating Token Index: 591