Model: GELU Model: 1 Layers, 2048 Neurons per Layer

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

Neuron 67 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Hooked Transformer Loading: HookedTransformer.from_pretrained('gelu-1l')

Click the toggle to see the full text!

Text #0

Max Range: 3.5228. Min Range: -3.5228

Max Act: 3.5228. Min Act: -0.1697

Data Index: 119190 (C4 (Web Text))

Max Activating Token Index: 834

Text #1

Max Range: 3.5228. Min Range: -3.5228

Max Act: 3.4635. Min Act: -0.1687

Data Index: 418516 (C4 (Web Text))

Max Activating Token Index: 108

Text #2

Max Range: 3.5228. Min Range: -3.5228

Max Act: 3.4497. Min Act: -0.1700

Data Index: 811329 (C4 (Web Text))

Max Activating Token Index: 978

Text #3

Max Range: 3.5228. Min Range: -3.5228

Max Act: 3.3920. Min Act: -0.1700

Data Index: 1206383 (C4 (Web Text))

Max Activating Token Index: 1022

Text #4

Max Range: 3.5228. Min Range: -3.5228

Max Act: 3.4161. Min Act: -0.1695

Data Index: 938591 (C4 (Web Text))

Max Activating Token Index: 74

Text #5

Max Range: 3.5228. Min Range: -3.5228

Max Act: 3.3819. Min Act: -0.1700

Data Index: 217496 (C4 (Web Text))

Max Activating Token Index: 118

Text #6

Max Range: 3.5228. Min Range: -3.5228

Max Act: 3.4127. Min Act: -0.1700

Data Index: 779537 (C4 (Web Text))

Max Activating Token Index: 620

Text #7

Max Range: 3.5228. Min Range: -3.5228

Max Act: 3.3478. Min Act: -0.1700

Data Index: 913139 (C4 (Web Text))

Max Activating Token Index: 896

Text #8

Max Range: 3.5228. Min Range: -3.5228

Max Act: 3.3558. Min Act: -0.1700

Data Index: 63074 (C4 (Web Text))

Max Activating Token Index: 86

Text #9

Max Range: 3.5228. Min Range: -3.5228

Max Act: 3.3662. Min Act: -0.1700

Data Index: 122032 (C4 (Web Text))

Max Activating Token Index: 185

Text #10

Max Range: 3.5228. Min Range: -3.5228

Max Act: 3.3500. Min Act: -0.1700

Data Index: 190172 (C4 (Web Text))

Max Activating Token Index: 28

Text #11

Max Range: 3.5228. Min Range: -3.5228

Max Act: 3.3556. Min Act: -0.1700

Data Index: 435604 (C4 (Web Text))

Max Activating Token Index: 811

Text #12

Max Range: 3.5228. Min Range: -3.5228

Max Act: 3.3788. Min Act: -0.1700

Data Index: 779553 (C4 (Web Text))

Max Activating Token Index: 264

Text #13

Max Range: 3.5228. Min Range: -3.5228

Max Act: 3.3720. Min Act: -0.1700

Data Index: 76231 (C4 (Web Text))

Max Activating Token Index: 27

Text #14

Max Range: 3.5228. Min Range: -3.5228

Max Act: 3.3359. Min Act: -0.1700

Data Index: 271795 (C4 (Web Text))

Max Activating Token Index: 851

Text #15

Max Range: 3.5228. Min Range: -3.5228

Max Act: 3.3366. Min Act: -0.1699

Data Index: 63254 (C4 (Web Text))

Max Activating Token Index: 736

Text #16

Max Range: 3.5228. Min Range: -3.5228

Max Act: 3.3454. Min Act: -0.1700

Data Index: 321100 (C4 (Web Text))

Max Activating Token Index: 485

Text #17

Max Range: 3.5228. Min Range: -3.5228

Max Act: 3.3477. Min Act: -0.1355

Data Index: 533266 (C4 (Web Text))

Max Activating Token Index: 1015

Text #18

Max Range: 3.5228. Min Range: -3.5228

Max Act: 3.3318. Min Act: -0.1700

Data Index: 849095 (C4 (Web Text))

Max Activating Token Index: 671

Text #19

Max Range: 3.5228. Min Range: -3.5228

Max Act: 3.3381. Min Act: -0.1700

Data Index: 904030 (C4 (Web Text))

Max Activating Token Index: 632