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

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

Neuron 58 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: 3.5419. Min Range: -3.5419

Max Act: 3.5419. Min Act: -0.1700

Data Index: 1252212 (C4 (Web Text))

Max Activating Token Index: 567

Text #1

Max Range: 3.5419. Min Range: -3.5419

Max Act: 3.3574. Min Act: -0.1698

Data Index: 267522 (C4 (Web Text))

Max Activating Token Index: 919

Text #2

Max Range: 3.5419. Min Range: -3.5419

Max Act: 3.3428. Min Act: -0.1698

Data Index: 699278 (C4 (Web Text))

Max Activating Token Index: 920

Text #3

Max Range: 3.5419. Min Range: -3.5419

Max Act: 3.3050. Min Act: -0.1699

Data Index: 1411498 (Python Code)

Max Activating Token Index: 289

Text #4

Max Range: 3.5419. Min Range: -3.5419

Max Act: 3.3030. Min Act: -0.1699

Data Index: 1049881 (C4 (Web Text))

Max Activating Token Index: 837

Text #5

Max Range: 3.5419. Min Range: -3.5419

Max Act: 3.3239. Min Act: -0.1698

Data Index: 976349 (C4 (Web Text))

Max Activating Token Index: 579

Text #6

Max Range: 3.5419. Min Range: -3.5419

Max Act: 3.2967. Min Act: -0.1698

Data Index: 1084609 (C4 (Web Text))

Max Activating Token Index: 705

Text #7

Max Range: 3.5419. Min Range: -3.5419

Max Act: 3.2687. Min Act: -0.1698

Data Index: 1634698 (Python Code)

Max Activating Token Index: 668

Text #8

Max Range: 3.5419. Min Range: -3.5419

Max Act: 3.2828. Min Act: -0.1698

Data Index: 1169318 (C4 (Web Text))

Max Activating Token Index: 179

Text #9

Max Range: 3.5419. Min Range: -3.5419

Max Act: 3.2263. Min Act: -0.1698

Data Index: 794862 (C4 (Web Text))

Max Activating Token Index: 819

Text #10

Max Range: 3.5419. Min Range: -3.5419

Max Act: 3.2264. Min Act: -0.1700

Data Index: 443050 (C4 (Web Text))

Max Activating Token Index: 987

Text #11

Max Range: 3.5419. Min Range: -3.5419

Max Act: 3.2105. Min Act: -0.1698

Data Index: 1128719 (C4 (Web Text))

Max Activating Token Index: 655

Text #12

Max Range: 3.5419. Min Range: -3.5419

Max Act: 3.2088. Min Act: -0.1700

Data Index: 415381 (C4 (Web Text))

Max Activating Token Index: 861

Text #13

Max Range: 3.5419. Min Range: -3.5419

Max Act: 3.2332. Min Act: -0.1700

Data Index: 176313 (C4 (Web Text))

Max Activating Token Index: 144

Text #14

Max Range: 3.5419. Min Range: -3.5419

Max Act: 3.2178. Min Act: -0.1700

Data Index: 1065802 (C4 (Web Text))

Max Activating Token Index: 851

Text #15

Max Range: 3.5419. Min Range: -3.5419

Max Act: 3.2103. Min Act: -0.1698

Data Index: 1003791 (C4 (Web Text))

Max Activating Token Index: 331

Text #16

Max Range: 3.5419. Min Range: -3.5419

Max Act: 3.2235. Min Act: -0.1699

Data Index: 224164 (C4 (Web Text))

Max Activating Token Index: 208

Text #17

Max Range: 3.5419. Min Range: -3.5419

Max Act: 3.2299. Min Act: -0.1700

Data Index: 971359 (C4 (Web Text))

Max Activating Token Index: 839

Text #18

Max Range: 3.5419. Min Range: -3.5419

Max Act: 3.1985. Min Act: -0.1698

Data Index: 502150 (C4 (Web Text))

Max Activating Token Index: 1023

Text #19

Max Range: 3.5419. Min Range: -3.5419

Max Act: 3.1903. Min Act: -0.1699

Data Index: 272379 (C4 (Web Text))

Max Activating Token Index: 649