Model: GELU Model: 2 Layers, 2048 Neurons per Layer

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

Neuron 383 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-2l')

Text #0

Max Range: 5.4513. Min Range: -5.4513

Max Act: 5.4513. Min Act: -0.1700

Data Index: 274684 (C4 (Web Text))

Max Activating Token Index: 217

Text #1

Max Range: 5.4513. Min Range: -5.4513

Max Act: 5.1076. Min Act: -0.1700

Data Index: 902057 (C4 (Web Text))

Max Activating Token Index: 820

Text #2

Max Range: 5.4513. Min Range: -5.4513

Max Act: 4.9826. Min Act: -0.1700

Data Index: 420956 (C4 (Web Text))

Max Activating Token Index: 458

Text #3

Max Range: 5.4513. Min Range: -5.4513

Max Act: 4.8888. Min Act: -0.1700

Data Index: 192849 (C4 (Web Text))

Max Activating Token Index: 288

Text #4

Max Range: 5.4513. Min Range: -5.4513

Max Act: 4.7951. Min Act: -0.1700

Data Index: 692863 (C4 (Web Text))

Max Activating Token Index: 999

Text #5

Max Range: 5.4513. Min Range: -5.4513

Max Act: 4.7326. Min Act: -0.1700

Data Index: 757344 (C4 (Web Text))

Max Activating Token Index: 340

Text #6

Max Range: 5.4513. Min Range: -5.4513

Max Act: 4.8263. Min Act: -0.1700

Data Index: 1158712 (C4 (Web Text))

Max Activating Token Index: 645

Text #7

Max Range: 5.4513. Min Range: -5.4513

Max Act: 4.8263. Min Act: -0.1700

Data Index: 1279767 (C4 (Web Text))

Max Activating Token Index: 872

Text #8

Max Range: 5.4513. Min Range: -5.4513

Max Act: 4.8263. Min Act: -0.1700

Data Index: 648661 (C4 (Web Text))

Max Activating Token Index: 640

Text #9

Max Range: 5.4513. Min Range: -5.4513

Max Act: 4.8576. Min Act: -0.1700

Data Index: 516502 (C4 (Web Text))

Max Activating Token Index: 489

Text #10

Max Range: 5.4513. Min Range: -5.4513

Max Act: 4.7638. Min Act: -0.1700

Data Index: 395735 (C4 (Web Text))

Max Activating Token Index: 311

Text #11

Max Range: 5.4513. Min Range: -5.4513

Max Act: 4.7638. Min Act: -0.1700

Data Index: 62009 (C4 (Web Text))

Max Activating Token Index: 572

Text #12

Max Range: 5.4513. Min Range: -5.4513

Max Act: 4.7013. Min Act: -0.1700

Data Index: 97779 (C4 (Web Text))

Max Activating Token Index: 829

Text #13

Max Range: 5.4513. Min Range: -5.4513

Max Act: 4.7013. Min Act: -0.1700

Data Index: 1277364 (C4 (Web Text))

Max Activating Token Index: 426

Text #14

Max Range: 5.4513. Min Range: -5.4513

Max Act: 4.7013. Min Act: -0.1700

Data Index: 1167177 (C4 (Web Text))

Max Activating Token Index: 255

Text #15

Max Range: 5.4513. Min Range: -5.4513

Max Act: 4.7013. Min Act: -0.1700

Data Index: 648787 (C4 (Web Text))

Max Activating Token Index: 384

Text #16

Max Range: 5.4513. Min Range: -5.4513

Max Act: 4.6701. Min Act: -0.1700

Data Index: 1144889 (C4 (Web Text))

Max Activating Token Index: 684

Text #17

Max Range: 5.4513. Min Range: -5.4513

Max Act: 4.6701. Min Act: -0.1700

Data Index: 930384 (C4 (Web Text))

Max Activating Token Index: 580

Text #18

Max Range: 5.4513. Min Range: -5.4513

Max Act: 4.6701. Min Act: -0.1700

Data Index: 1016332 (C4 (Web Text))

Max Activating Token Index: 929

Text #19

Max Range: 5.4513. Min Range: -5.4513

Max Act: 4.6701. Min Act: -0.1700

Data Index: 1341194 (C4 (Web Text))

Max Activating Token Index: 488