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

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

Neuron 1459 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 7.6011. Min Range: -7.6011

Max Act: 7.6011. Min Act: -0.1700

Data Index: 176704 (C4 (Web Text))

Max Activating Token Index: 563

Text #1

Max Range: 7.6011. Min Range: -7.6011

Max Act: 7.5386. Min Act: -0.1700

Data Index: 1032682 (C4 (Web Text))

Max Activating Token Index: 628

Text #2

Max Range: 7.6011. Min Range: -7.6011

Max Act: 7.4761. Min Act: -0.1697

Data Index: 1187229 (C4 (Web Text))

Max Activating Token Index: 896

Text #3

Max Range: 7.6011. Min Range: -7.6011

Max Act: 7.2261. Min Act: -0.1700

Data Index: 172152 (C4 (Web Text))

Max Activating Token Index: 302

Text #4

Max Range: 7.6011. Min Range: -7.6011

Max Act: 7.2261. Min Act: -0.1699

Data Index: 856694 (C4 (Web Text))

Max Activating Token Index: 565

Text #5

Max Range: 7.6011. Min Range: -7.6011

Max Act: 7.1011. Min Act: -0.1700

Data Index: 650335 (C4 (Web Text))

Max Activating Token Index: 446

Text #6

Max Range: 7.6011. Min Range: -7.6011

Max Act: 7.1323. Min Act: -0.1700

Data Index: 26447 (C4 (Web Text))

Max Activating Token Index: 866

Text #7

Max Range: 7.6011. Min Range: -7.6011

Max Act: 7.0698. Min Act: -0.1700

Data Index: 978967 (C4 (Web Text))

Max Activating Token Index: 1000

Text #8

Max Range: 7.6011. Min Range: -7.6011

Max Act: 7.0698. Min Act: -0.1700

Data Index: 392001 (C4 (Web Text))

Max Activating Token Index: 933

Text #9

Max Range: 7.6011. Min Range: -7.6011

Max Act: 7.0386. Min Act: -0.1700

Data Index: 446992 (C4 (Web Text))

Max Activating Token Index: 979

Text #10

Max Range: 7.6011. Min Range: -7.6011

Max Act: 7.1636. Min Act: -0.1700

Data Index: 362233 (C4 (Web Text))

Max Activating Token Index: 152

Text #11

Max Range: 7.6011. Min Range: -7.6011

Max Act: 7.0386. Min Act: -0.1700

Data Index: 857019 (C4 (Web Text))

Max Activating Token Index: 310

Text #12

Max Range: 7.6011. Min Range: -7.6011

Max Act: 7.1011. Min Act: -0.1700

Data Index: 332334 (C4 (Web Text))

Max Activating Token Index: 359

Text #13

Max Range: 7.6011. Min Range: -7.6011

Max Act: 7.0698. Min Act: -0.1700

Data Index: 937363 (C4 (Web Text))

Max Activating Token Index: 681

Text #14

Max Range: 7.6011. Min Range: -7.6011

Max Act: 7.0073. Min Act: -0.1700

Data Index: 1129634 (C4 (Web Text))

Max Activating Token Index: 277

Text #15

Max Range: 7.6011. Min Range: -7.6011

Max Act: 7.0386. Min Act: -0.1700

Data Index: 1044731 (C4 (Web Text))

Max Activating Token Index: 664

Text #16

Max Range: 7.6011. Min Range: -7.6011

Max Act: 7.0386. Min Act: -0.1700

Data Index: 1198490 (C4 (Web Text))

Max Activating Token Index: 786

Text #17

Max Range: 7.6011. Min Range: -7.6011

Max Act: 7.0073. Min Act: -0.1700

Data Index: 1076235 (C4 (Web Text))

Max Activating Token Index: 913

Text #18

Max Range: 7.6011. Min Range: -7.6011

Max Act: 6.8198. Min Act: -0.1700

Data Index: 31460 (C4 (Web Text))

Max Activating Token Index: 726

Text #19

Max Range: 7.6011. Min Range: -7.6011

Max Act: 6.9448. Min Act: -0.1699

Data Index: 541419 (C4 (Web Text))

Max Activating Token Index: 579