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

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

Neuron 13 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: 3.7382. Min Range: -3.7382

Max Act: 3.7382. Min Act: -0.1700

Data Index: 1032250 (C4 (Web Text))

Max Activating Token Index: 144

Text #1

Max Range: 3.7382. Min Range: -3.7382

Max Act: 3.5504. Min Act: -0.1700

Data Index: 1145563 (C4 (Web Text))

Max Activating Token Index: 343

Text #2

Max Range: 3.7382. Min Range: -3.7382

Max Act: 3.4720. Min Act: -0.1700

Data Index: 834958 (C4 (Web Text))

Max Activating Token Index: 730

Text #3

Max Range: 3.7382. Min Range: -3.7382

Max Act: 3.5190. Min Act: -0.1700

Data Index: 2932 (C4 (Web Text))

Max Activating Token Index: 235

Text #4

Max Range: 3.7382. Min Range: -3.7382

Max Act: 3.5034. Min Act: -0.1700

Data Index: 358292 (C4 (Web Text))

Max Activating Token Index: 298

Text #5

Max Range: 3.7382. Min Range: -3.7382

Max Act: 3.4877. Min Act: -0.1700

Data Index: 204220 (C4 (Web Text))

Max Activating Token Index: 808

Text #6

Max Range: 3.7382. Min Range: -3.7382

Max Act: 3.4720. Min Act: -0.1700

Data Index: 1250810 (C4 (Web Text))

Max Activating Token Index: 414

Text #7

Max Range: 3.7382. Min Range: -3.7382

Max Act: 3.4250. Min Act: -0.1700

Data Index: 206171 (C4 (Web Text))

Max Activating Token Index: 662

Text #8

Max Range: 3.7382. Min Range: -3.7382

Max Act: 3.4877. Min Act: -0.1700

Data Index: 500816 (C4 (Web Text))

Max Activating Token Index: 911

Text #9

Max Range: 3.7382. Min Range: -3.7382

Max Act: 3.4720. Min Act: -0.1700

Data Index: 556255 (C4 (Web Text))

Max Activating Token Index: 139

Text #10

Max Range: 3.7382. Min Range: -3.7382

Max Act: 3.4564. Min Act: -0.1700

Data Index: 262350 (C4 (Web Text))

Max Activating Token Index: 748

Text #11

Max Range: 3.7382. Min Range: -3.7382

Max Act: 3.4564. Min Act: -0.1700

Data Index: 1011867 (C4 (Web Text))

Max Activating Token Index: 479

Text #12

Max Range: 3.7382. Min Range: -3.7382

Max Act: 3.3936. Min Act: -0.1700

Data Index: 819959 (C4 (Web Text))

Max Activating Token Index: 1022

Text #13

Max Range: 3.7382. Min Range: -3.7382

Max Act: 3.4564. Min Act: -0.1700

Data Index: 185086 (C4 (Web Text))

Max Activating Token Index: 521

Text #14

Max Range: 3.7382. Min Range: -3.7382

Max Act: 3.3779. Min Act: -0.1700

Data Index: 1334029 (C4 (Web Text))

Max Activating Token Index: 876

Text #15

Max Range: 3.7382. Min Range: -3.7382

Max Act: 3.3936. Min Act: -0.1700

Data Index: 485066 (C4 (Web Text))

Max Activating Token Index: 72

Text #16

Max Range: 3.7382. Min Range: -3.7382

Max Act: 3.4407. Min Act: -0.1700

Data Index: 535012 (C4 (Web Text))

Max Activating Token Index: 57

Text #17

Max Range: 3.7382. Min Range: -3.7382

Max Act: 3.4250. Min Act: -0.1700

Data Index: 1131723 (C4 (Web Text))

Max Activating Token Index: 796

Text #18

Max Range: 3.7382. Min Range: -3.7382

Max Act: 3.4720. Min Act: -0.1700

Data Index: 674625 (C4 (Web Text))

Max Activating Token Index: 89

Text #19

Max Range: 3.7382. Min Range: -3.7382

Max Act: 3.3936. Min Act: -0.1700

Data Index: 275251 (C4 (Web Text))

Max Activating Token Index: 676