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

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

Neuron 122 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: 3.4764. Min Range: -3.4764

Max Act: 3.4764. Min Act: -0.1700

Data Index: 518263 (C4 (Web Text))

Max Activating Token Index: 684

Text #1

Max Range: 3.4764. Min Range: -3.4764

Max Act: 3.4764. Min Act: -0.1700

Data Index: 604851 (C4 (Web Text))

Max Activating Token Index: 857

Text #2

Max Range: 3.4764. Min Range: -3.4764

Max Act: 3.3823. Min Act: -0.1700

Data Index: 204728 (C4 (Web Text))

Max Activating Token Index: 64

Text #3

Max Range: 3.4764. Min Range: -3.4764

Max Act: 3.3352. Min Act: -0.1700

Data Index: 691484 (C4 (Web Text))

Max Activating Token Index: 812

Text #4

Max Range: 3.4764. Min Range: -3.4764

Max Act: 3.3352. Min Act: -0.1700

Data Index: 338143 (C4 (Web Text))

Max Activating Token Index: 898

Text #5

Max Range: 3.4764. Min Range: -3.4764

Max Act: 3.3352. Min Act: -0.1700

Data Index: 675631 (C4 (Web Text))

Max Activating Token Index: 430

Text #6

Max Range: 3.4764. Min Range: -3.4764

Max Act: 3.2881. Min Act: -0.1700

Data Index: 36310 (C4 (Web Text))

Max Activating Token Index: 571

Text #7

Max Range: 3.4764. Min Range: -3.4764

Max Act: 3.3666. Min Act: -0.1700

Data Index: 583081 (C4 (Web Text))

Max Activating Token Index: 818

Text #8

Max Range: 3.4764. Min Range: -3.4764

Max Act: 3.3352. Min Act: -0.1700

Data Index: 114255 (C4 (Web Text))

Max Activating Token Index: 545

Text #9

Max Range: 3.4764. Min Range: -3.4764

Max Act: 3.3195. Min Act: -0.1700

Data Index: 551772 (C4 (Web Text))

Max Activating Token Index: 147

Text #10

Max Range: 3.4764. Min Range: -3.4764

Max Act: 3.3195. Min Act: -0.1700

Data Index: 785850 (C4 (Web Text))

Max Activating Token Index: 27

Text #11

Max Range: 3.4764. Min Range: -3.4764

Max Act: 3.3195. Min Act: -0.1700

Data Index: 521711 (C4 (Web Text))

Max Activating Token Index: 366

Text #12

Max Range: 3.4764. Min Range: -3.4764

Max Act: 3.3038. Min Act: -0.1700

Data Index: 34987 (C4 (Web Text))

Max Activating Token Index: 543

Text #13

Max Range: 3.4764. Min Range: -3.4764

Max Act: 3.3352. Min Act: -0.1700

Data Index: 1246866 (C4 (Web Text))

Max Activating Token Index: 121

Text #14

Max Range: 3.4764. Min Range: -3.4764

Max Act: 3.2881. Min Act: -0.1700

Data Index: 1121616 (C4 (Web Text))

Max Activating Token Index: 866

Text #15

Max Range: 3.4764. Min Range: -3.4764

Max Act: 3.3195. Min Act: -0.1700

Data Index: 485468 (C4 (Web Text))

Max Activating Token Index: 973

Text #16

Max Range: 3.4764. Min Range: -3.4764

Max Act: 3.3195. Min Act: -0.1700

Data Index: 286678 (C4 (Web Text))

Max Activating Token Index: 814

Text #17

Max Range: 3.4764. Min Range: -3.4764

Max Act: 3.3195. Min Act: -0.1700

Data Index: 446123 (C4 (Web Text))

Max Activating Token Index: 847

Text #18

Max Range: 3.4764. Min Range: -3.4764

Max Act: 3.3195. Min Act: -0.1700

Data Index: 68266 (C4 (Web Text))

Max Activating Token Index: 728

Text #19

Max Range: 3.4764. Min Range: -3.4764

Max Act: 3.2724. Min Act: -0.1700

Data Index: 1280012 (C4 (Web Text))

Max Activating Token Index: 581