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

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

Neuron 1338 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: 17.6143. Min Range: -17.6143

Max Act: 17.6143. Min Act: -0.1700

Data Index: 1075609 (C4 (Web Text))

Max Activating Token Index: 500

Text #1

Max Range: 17.6143. Min Range: -17.6143

Max Act: 17.3616. Min Act: -0.1700

Data Index: 241657 (C4 (Web Text))

Max Activating Token Index: 1008

Text #2

Max Range: 17.6143. Min Range: -17.6143

Max Act: 16.5490. Min Act: -0.1700

Data Index: 1372470 (Python Code)

Max Activating Token Index: 246

Text #3

Max Range: 17.6143. Min Range: -17.6143

Max Act: 16.5035. Min Act: -0.1700

Data Index: 694225 (C4 (Web Text))

Max Activating Token Index: 369

Text #4

Max Range: 17.6143. Min Range: -17.6143

Max Act: 16.4887. Min Act: -0.1700

Data Index: 61990 (C4 (Web Text))

Max Activating Token Index: 684

Text #5

Max Range: 17.6143. Min Range: -17.6143

Max Act: 16.3291. Min Act: -0.1700

Data Index: 157390 (C4 (Web Text))

Max Activating Token Index: 790

Text #6

Max Range: 17.6143. Min Range: -17.6143

Max Act: 16.2149. Min Act: -0.1700

Data Index: 1317486 (C4 (Web Text))

Max Activating Token Index: 862

Text #7

Max Range: 17.6143. Min Range: -17.6143

Max Act: 16.1297. Min Act: -0.1700

Data Index: 1186184 (C4 (Web Text))

Max Activating Token Index: 282

Text #8

Max Range: 17.6143. Min Range: -17.6143

Max Act: 16.0390. Min Act: -0.1700

Data Index: 1273769 (C4 (Web Text))

Max Activating Token Index: 824

Text #9

Max Range: 17.6143. Min Range: -17.6143

Max Act: 15.9376. Min Act: -0.1700

Data Index: 1147649 (C4 (Web Text))

Max Activating Token Index: 509

Text #10

Max Range: 17.6143. Min Range: -17.6143

Max Act: 15.9346. Min Act: -0.1700

Data Index: 165014 (C4 (Web Text))

Max Activating Token Index: 700

Text #11

Max Range: 17.6143. Min Range: -17.6143

Max Act: 15.8899. Min Act: -0.1700

Data Index: 1323574 (C4 (Web Text))

Max Activating Token Index: 909

Text #12

Max Range: 17.6143. Min Range: -17.6143

Max Act: 15.9157. Min Act: -0.1700

Data Index: 155363 (C4 (Web Text))

Max Activating Token Index: 707

Text #13

Max Range: 17.6143. Min Range: -17.6143

Max Act: 15.9147. Min Act: -0.1700

Data Index: 1232359 (C4 (Web Text))

Max Activating Token Index: 391

Text #14

Max Range: 17.6143. Min Range: -17.6143

Max Act: 15.8308. Min Act: -0.1700

Data Index: 145543 (C4 (Web Text))

Max Activating Token Index: 367

Text #15

Max Range: 17.6143. Min Range: -17.6143

Max Act: 15.7925. Min Act: -0.1700

Data Index: 746682 (C4 (Web Text))

Max Activating Token Index: 887

Text #16

Max Range: 17.6143. Min Range: -17.6143

Max Act: 15.8371. Min Act: -0.1700

Data Index: 112234 (C4 (Web Text))

Max Activating Token Index: 346

Text #17

Max Range: 17.6143. Min Range: -17.6143

Max Act: 15.8674. Min Act: -0.1700

Data Index: 739569 (C4 (Web Text))

Max Activating Token Index: 116

Text #18

Max Range: 17.6143. Min Range: -17.6143

Max Act: 15.6326. Min Act: -0.1700

Data Index: 224075 (C4 (Web Text))

Max Activating Token Index: 255

Text #19

Max Range: 17.6143. Min Range: -17.6143

Max Act: 15.7137. Min Act: -0.1700

Data Index: 797805 (C4 (Web Text))

Max Activating Token Index: 959