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

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

Neuron 217 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: 5.2164. Min Range: -5.2164

Max Act: 5.2155. Min Act: -0.1700

Data Index: 728166 (C4 (Web Text))

Max Activating Token Index: 528

Text #1

Max Range: 5.2164. Min Range: -5.2164

Max Act: 5.1918. Min Act: -0.1700

Data Index: 934986 (C4 (Web Text))

Max Activating Token Index: 108

Text #2

Max Range: 5.2164. Min Range: -5.2164

Max Act: 5.2164. Min Act: -0.1700

Data Index: 1585478 (Python Code)

Max Activating Token Index: 769

Text #3

Max Range: 5.2164. Min Range: -5.2164

Max Act: 5.1010. Min Act: -0.1699

Data Index: 469444 (C4 (Web Text))

Max Activating Token Index: 52

Text #4

Max Range: 5.2164. Min Range: -5.2164

Max Act: 5.0792. Min Act: -0.1700

Data Index: 1510680 (Python Code)

Max Activating Token Index: 289

Text #5

Max Range: 5.2164. Min Range: -5.2164

Max Act: 5.0571. Min Act: -0.1700

Data Index: 978991 (C4 (Web Text))

Max Activating Token Index: 24

Text #6

Max Range: 5.2164. Min Range: -5.2164

Max Act: 5.0389. Min Act: -0.1700

Data Index: 161269 (C4 (Web Text))

Max Activating Token Index: 444

Text #7

Max Range: 5.2164. Min Range: -5.2164

Max Act: 5.0536. Min Act: -0.1700

Data Index: 1500483 (Python Code)

Max Activating Token Index: 869

Text #8

Max Range: 5.2164. Min Range: -5.2164

Max Act: 5.0338. Min Act: -0.1700

Data Index: 1288334 (C4 (Web Text))

Max Activating Token Index: 437

Text #9

Max Range: 5.2164. Min Range: -5.2164

Max Act: 5.0340. Min Act: -0.1700

Data Index: 1386231 (Python Code)

Max Activating Token Index: 251

Text #10

Max Range: 5.2164. Min Range: -5.2164

Max Act: 5.0082. Min Act: -0.1700

Data Index: 241070 (C4 (Web Text))

Max Activating Token Index: 15

Text #11

Max Range: 5.2164. Min Range: -5.2164

Max Act: 5.0037. Min Act: -0.1700

Data Index: 1125907 (C4 (Web Text))

Max Activating Token Index: 812

Text #12

Max Range: 5.2164. Min Range: -5.2164

Max Act: 4.9903. Min Act: -0.1700

Data Index: 156839 (C4 (Web Text))

Max Activating Token Index: 521

Text #13

Max Range: 5.2164. Min Range: -5.2164

Max Act: 4.9746. Min Act: -0.1700

Data Index: 188601 (C4 (Web Text))

Max Activating Token Index: 112

Text #14

Max Range: 5.2164. Min Range: -5.2164

Max Act: 4.9950. Min Act: -0.1700

Data Index: 1099446 (C4 (Web Text))

Max Activating Token Index: 436

Text #15

Max Range: 5.2164. Min Range: -5.2164

Max Act: 5.0012. Min Act: -0.1700

Data Index: 88726 (C4 (Web Text))

Max Activating Token Index: 481

Text #16

Max Range: 5.2164. Min Range: -5.2164

Max Act: 4.9621. Min Act: -0.1699

Data Index: 224653 (C4 (Web Text))

Max Activating Token Index: 633

Text #17

Max Range: 5.2164. Min Range: -5.2164

Max Act: 4.9305. Min Act: -0.1700

Data Index: 1554581 (Python Code)

Max Activating Token Index: 479

Text #18

Max Range: 5.2164. Min Range: -5.2164

Max Act: 4.9022. Min Act: -0.1700

Data Index: 626240 (C4 (Web Text))

Max Activating Token Index: 727

Text #19

Max Range: 5.2164. Min Range: -5.2164

Max Act: 4.9281. Min Act: -0.1700

Data Index: 1074554 (C4 (Web Text))

Max Activating Token Index: 18