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

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

Neuron 428 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: 3.5323. Min Range: -3.5323

Max Act: 3.5323. Min Act: -0.1700

Data Index: 1096006 (C4 (Web Text))

Max Activating Token Index: 176

Text #1

Max Range: 3.5323. Min Range: -3.5323

Max Act: 3.3094. Min Act: -0.1700

Data Index: 627388 (C4 (Web Text))

Max Activating Token Index: 178

Text #2

Max Range: 3.5323. Min Range: -3.5323

Max Act: 3.3089. Min Act: -0.1700

Data Index: 251123 (C4 (Web Text))

Max Activating Token Index: 1022

Text #3

Max Range: 3.5323. Min Range: -3.5323

Max Act: 3.2886. Min Act: -0.1700

Data Index: 894768 (C4 (Web Text))

Max Activating Token Index: 852

Text #4

Max Range: 3.5323. Min Range: -3.5323

Max Act: 3.2779. Min Act: -0.1700

Data Index: 701765 (C4 (Web Text))

Max Activating Token Index: 910

Text #5

Max Range: 3.5323. Min Range: -3.5323

Max Act: 3.2691. Min Act: -0.1699

Data Index: 1238601 (C4 (Web Text))

Max Activating Token Index: 719

Text #6

Max Range: 3.5323. Min Range: -3.5323

Max Act: 3.2534. Min Act: -0.1700

Data Index: 458269 (C4 (Web Text))

Max Activating Token Index: 919

Text #7

Max Range: 3.5323. Min Range: -3.5323

Max Act: 3.2667. Min Act: -0.1700

Data Index: 663347 (C4 (Web Text))

Max Activating Token Index: 682

Text #8

Max Range: 3.5323. Min Range: -3.5323

Max Act: 3.2508. Min Act: -0.1700

Data Index: 215105 (C4 (Web Text))

Max Activating Token Index: 39

Text #9

Max Range: 3.5323. Min Range: -3.5323

Max Act: 3.2319. Min Act: -0.1700

Data Index: 851083 (C4 (Web Text))

Max Activating Token Index: 450

Text #10

Max Range: 3.5323. Min Range: -3.5323

Max Act: 3.2197. Min Act: -0.1696

Data Index: 504270 (C4 (Web Text))

Max Activating Token Index: 792

Text #11

Max Range: 3.5323. Min Range: -3.5323

Max Act: 3.2191. Min Act: -0.1700

Data Index: 249276 (C4 (Web Text))

Max Activating Token Index: 816

Text #12

Max Range: 3.5323. Min Range: -3.5323

Max Act: 3.2337. Min Act: -0.1700

Data Index: 192859 (C4 (Web Text))

Max Activating Token Index: 74

Text #13

Max Range: 3.5323. Min Range: -3.5323

Max Act: 3.2185. Min Act: -0.1700

Data Index: 179754 (C4 (Web Text))

Max Activating Token Index: 74

Text #14

Max Range: 3.5323. Min Range: -3.5323

Max Act: 3.2144. Min Act: -0.1700

Data Index: 982331 (C4 (Web Text))

Max Activating Token Index: 428

Text #15

Max Range: 3.5323. Min Range: -3.5323

Max Act: 3.2120. Min Act: -0.1700

Data Index: 724165 (C4 (Web Text))

Max Activating Token Index: 629

Text #16

Max Range: 3.5323. Min Range: -3.5323

Max Act: 3.1995. Min Act: -0.1700

Data Index: 203474 (C4 (Web Text))

Max Activating Token Index: 51

Text #17

Max Range: 3.5323. Min Range: -3.5323

Max Act: 3.2229. Min Act: -0.1700

Data Index: 1041972 (C4 (Web Text))

Max Activating Token Index: 599

Text #18

Max Range: 3.5323. Min Range: -3.5323

Max Act: 3.1998. Min Act: -0.1700

Data Index: 5740 (C4 (Web Text))

Max Activating Token Index: 627

Text #19

Max Range: 3.5323. Min Range: -3.5323

Max Act: 3.1962. Min Act: -0.1700

Data Index: 211402 (C4 (Web Text))

Max Activating Token Index: 669