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

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

Neuron 431 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.7427. Min Range: -5.7427

Max Act: 5.7427. Min Act: -0.1700

Data Index: 1200228 (C4 (Web Text))

Max Activating Token Index: 780

Text #1

Max Range: 5.7427. Min Range: -5.7427

Max Act: 5.7115. Min Act: -0.1700

Data Index: 1040103 (C4 (Web Text))

Max Activating Token Index: 841

Text #2

Max Range: 5.7427. Min Range: -5.7427

Max Act: 5.6802. Min Act: -0.1700

Data Index: 204023 (C4 (Web Text))

Max Activating Token Index: 293

Text #3

Max Range: 5.7427. Min Range: -5.7427

Max Act: 5.5865. Min Act: -0.1700

Data Index: 1203333 (C4 (Web Text))

Max Activating Token Index: 917

Text #4

Max Range: 5.7427. Min Range: -5.7427

Max Act: 5.5552. Min Act: -0.1700

Data Index: 650300 (C4 (Web Text))

Max Activating Token Index: 702

Text #5

Max Range: 5.7427. Min Range: -5.7427

Max Act: 5.5240. Min Act: -0.1700

Data Index: 924555 (C4 (Web Text))

Max Activating Token Index: 790

Text #6

Max Range: 5.7427. Min Range: -5.7427

Max Act: 5.4927. Min Act: -0.1700

Data Index: 1050800 (C4 (Web Text))

Max Activating Token Index: 213

Text #7

Max Range: 5.7427. Min Range: -5.7427

Max Act: 5.4927. Min Act: -0.1700

Data Index: 99182 (C4 (Web Text))

Max Activating Token Index: 198

Text #8

Max Range: 5.7427. Min Range: -5.7427

Max Act: 5.4927. Min Act: -0.1700

Data Index: 3805 (C4 (Web Text))

Max Activating Token Index: 987

Text #9

Max Range: 5.7427. Min Range: -5.7427

Max Act: 5.5552. Min Act: -0.1700

Data Index: 330917 (C4 (Web Text))

Max Activating Token Index: 421

Text #10

Max Range: 5.7427. Min Range: -5.7427

Max Act: 5.4302. Min Act: -0.1700

Data Index: 632815 (C4 (Web Text))

Max Activating Token Index: 684

Text #11

Max Range: 5.7427. Min Range: -5.7427

Max Act: 5.3990. Min Act: -0.1700

Data Index: 1277282 (C4 (Web Text))

Max Activating Token Index: 236

Text #12

Max Range: 5.7427. Min Range: -5.7427

Max Act: 5.3677. Min Act: -0.1700

Data Index: 1142812 (C4 (Web Text))

Max Activating Token Index: 924

Text #13

Max Range: 5.7427. Min Range: -5.7427

Max Act: 5.4615. Min Act: -0.1700

Data Index: 52405 (C4 (Web Text))

Max Activating Token Index: 950

Text #14

Max Range: 5.7427. Min Range: -5.7427

Max Act: 5.3990. Min Act: -0.1700

Data Index: 391066 (C4 (Web Text))

Max Activating Token Index: 680

Text #15

Max Range: 5.7427. Min Range: -5.7427

Max Act: 5.3677. Min Act: -0.1700

Data Index: 1016048 (C4 (Web Text))

Max Activating Token Index: 627

Text #16

Max Range: 5.7427. Min Range: -5.7427

Max Act: 5.3677. Min Act: -0.1700

Data Index: 311411 (C4 (Web Text))

Max Activating Token Index: 800

Text #17

Max Range: 5.7427. Min Range: -5.7427

Max Act: 5.3677. Min Act: -0.1700

Data Index: 557898 (C4 (Web Text))

Max Activating Token Index: 134

Text #18

Max Range: 5.7427. Min Range: -5.7427

Max Act: 5.3677. Min Act: -0.1700

Data Index: 945413 (C4 (Web Text))

Max Activating Token Index: 993

Text #19

Max Range: 5.7427. Min Range: -5.7427

Max Act: 5.3677. Min Act: -0.1700

Data Index: 113979 (C4 (Web Text))

Max Activating Token Index: 125