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

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

Neuron 1326 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.0166. Min Range: -4.0166

Max Act: 3.9854. Min Act: -0.1700

Data Index: 85201 (C4 (Web Text))

Max Activating Token Index: 809

Text #1

Max Range: 4.0166. Min Range: -4.0166

Max Act: 4.0166. Min Act: -0.1700

Data Index: 166022 (C4 (Web Text))

Max Activating Token Index: 920

Text #2

Max Range: 4.0166. Min Range: -4.0166

Max Act: 3.6413. Min Act: -0.1700

Data Index: 931938 (C4 (Web Text))

Max Activating Token Index: 794

Text #3

Max Range: 4.0166. Min Range: -4.0166

Max Act: 3.7351. Min Act: -0.1700

Data Index: 409620 (C4 (Web Text))

Max Activating Token Index: 779

Text #4

Max Range: 4.0166. Min Range: -4.0166

Max Act: 3.6882. Min Act: -0.1700

Data Index: 396680 (C4 (Web Text))

Max Activating Token Index: 860

Text #5

Max Range: 4.0166. Min Range: -4.0166

Max Act: 3.7664. Min Act: -0.1700

Data Index: 65085 (C4 (Web Text))

Max Activating Token Index: 377

Text #6

Max Range: 4.0166. Min Range: -4.0166

Max Act: 3.7977. Min Act: -0.1700

Data Index: 1177235 (C4 (Web Text))

Max Activating Token Index: 942

Text #7

Max Range: 4.0166. Min Range: -4.0166

Max Act: 3.7821. Min Act: -0.1700

Data Index: 680753 (C4 (Web Text))

Max Activating Token Index: 757

Text #8

Max Range: 4.0166. Min Range: -4.0166

Max Act: 3.7195. Min Act: -0.1700

Data Index: 593886 (C4 (Web Text))

Max Activating Token Index: 940

Text #9

Max Range: 4.0166. Min Range: -4.0166

Max Act: 3.7508. Min Act: -0.1700

Data Index: 731009 (C4 (Web Text))

Max Activating Token Index: 341

Text #10

Max Range: 4.0166. Min Range: -4.0166

Max Act: 3.7039. Min Act: -0.1700

Data Index: 26015 (C4 (Web Text))

Max Activating Token Index: 501

Text #11

Max Range: 4.0166. Min Range: -4.0166

Max Act: 3.6569. Min Act: -0.1700

Data Index: 957997 (C4 (Web Text))

Max Activating Token Index: 267

Text #12

Max Range: 4.0166. Min Range: -4.0166

Max Act: 3.5003. Min Act: -0.1700

Data Index: 1150994 (C4 (Web Text))

Max Activating Token Index: 1020

Text #13

Max Range: 4.0166. Min Range: -4.0166

Max Act: 3.7039. Min Act: -0.1700

Data Index: 383976 (C4 (Web Text))

Max Activating Token Index: 627

Text #14

Max Range: 4.0166. Min Range: -4.0166

Max Act: 3.6569. Min Act: -0.1700

Data Index: 583690 (C4 (Web Text))

Max Activating Token Index: 509

Text #15

Max Range: 4.0166. Min Range: -4.0166

Max Act: 3.6726. Min Act: -0.1700

Data Index: 466635 (C4 (Web Text))

Max Activating Token Index: 764

Text #16

Max Range: 4.0166. Min Range: -4.0166

Max Act: 3.7195. Min Act: -0.1700

Data Index: 409941 (C4 (Web Text))

Max Activating Token Index: 966

Text #17

Max Range: 4.0166. Min Range: -4.0166

Max Act: 3.6256. Min Act: -0.1700

Data Index: 27968 (C4 (Web Text))

Max Activating Token Index: 459

Text #18

Max Range: 4.0166. Min Range: -4.0166

Max Act: 3.6099. Min Act: -0.1700

Data Index: 1180782 (C4 (Web Text))

Max Activating Token Index: 966

Text #19

Max Range: 4.0166. Min Range: -4.0166

Max Act: 3.6099. Min Act: -0.1700

Data Index: 167055 (C4 (Web Text))

Max Activating Token Index: 121