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

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

Neuron 1314 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: 5.8020. Min Range: -5.8020

Max Act: 5.8020. Min Act: -0.1700

Data Index: 1064275 (C4 (Web Text))

Max Activating Token Index: 913

Text #1

Max Range: 5.8020. Min Range: -5.8020

Max Act: 5.7395. Min Act: -0.1700

Data Index: 974458 (C4 (Web Text))

Max Activating Token Index: 273

Text #2

Max Range: 5.8020. Min Range: -5.8020

Max Act: 5.5520. Min Act: -0.1699

Data Index: 1194327 (C4 (Web Text))

Max Activating Token Index: 683

Text #3

Max Range: 5.8020. Min Range: -5.8020

Max Act: 5.5832. Min Act: -0.1700

Data Index: 5218 (C4 (Web Text))

Max Activating Token Index: 204

Text #4

Max Range: 5.8020. Min Range: -5.8020

Max Act: 5.5520. Min Act: -0.1700

Data Index: 901523 (C4 (Web Text))

Max Activating Token Index: 160

Text #5

Max Range: 5.8020. Min Range: -5.8020

Max Act: 5.5520. Min Act: -0.1700

Data Index: 480040 (C4 (Web Text))

Max Activating Token Index: 542

Text #6

Max Range: 5.8020. Min Range: -5.8020

Max Act: 5.5832. Min Act: -0.1700

Data Index: 333651 (C4 (Web Text))

Max Activating Token Index: 116

Text #7

Max Range: 5.8020. Min Range: -5.8020

Max Act: 5.5207. Min Act: -0.1700

Data Index: 101217 (C4 (Web Text))

Max Activating Token Index: 459

Text #8

Max Range: 5.8020. Min Range: -5.8020

Max Act: 5.5207. Min Act: -0.1700

Data Index: 436624 (C4 (Web Text))

Max Activating Token Index: 455

Text #9

Max Range: 5.8020. Min Range: -5.8020

Max Act: 5.4895. Min Act: -0.1699

Data Index: 701934 (C4 (Web Text))

Max Activating Token Index: 698

Text #10

Max Range: 5.8020. Min Range: -5.8020

Max Act: 5.3957. Min Act: -0.1700

Data Index: 993544 (C4 (Web Text))

Max Activating Token Index: 417

Text #11

Max Range: 5.8020. Min Range: -5.8020

Max Act: 5.3645. Min Act: -0.1700

Data Index: 792155 (C4 (Web Text))

Max Activating Token Index: 1009

Text #12

Max Range: 5.8020. Min Range: -5.8020

Max Act: 5.3957. Min Act: -0.1700

Data Index: 179576 (C4 (Web Text))

Max Activating Token Index: 992

Text #13

Max Range: 5.8020. Min Range: -5.8020

Max Act: 5.3332. Min Act: -0.1700

Data Index: 707100 (C4 (Web Text))

Max Activating Token Index: 936

Text #14

Max Range: 5.8020. Min Range: -5.8020

Max Act: 5.3957. Min Act: -0.1700

Data Index: 1188265 (C4 (Web Text))

Max Activating Token Index: 316

Text #15

Max Range: 5.8020. Min Range: -5.8020

Max Act: 5.3645. Min Act: -0.1700

Data Index: 145409 (C4 (Web Text))

Max Activating Token Index: 64

Text #16

Max Range: 5.8020. Min Range: -5.8020

Max Act: 5.3332. Min Act: -0.1700

Data Index: 970719 (C4 (Web Text))

Max Activating Token Index: 719

Text #17

Max Range: 5.8020. Min Range: -5.8020

Max Act: 5.3020. Min Act: -0.1700

Data Index: 1033245 (C4 (Web Text))

Max Activating Token Index: 453

Text #18

Max Range: 5.8020. Min Range: -5.8020

Max Act: 5.3957. Min Act: -0.1700

Data Index: 473773 (C4 (Web Text))

Max Activating Token Index: 337

Text #19

Max Range: 5.8020. Min Range: -5.8020

Max Act: 5.3020. Min Act: -0.1700

Data Index: 1063552 (C4 (Web Text))

Max Activating Token Index: 994