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

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

Neuron 1396 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: 3.4098. Min Range: -3.4098

Max Act: 3.4098. Min Act: -0.1699

Data Index: 947040 (C4 (Web Text))

Max Activating Token Index: 374

Text #1

Max Range: 3.4098. Min Range: -3.4098

Max Act: 3.4046. Min Act: -0.1699

Data Index: 153627 (C4 (Web Text))

Max Activating Token Index: 268

Text #2

Max Range: 3.4098. Min Range: -3.4098

Max Act: 3.3359. Min Act: -0.1668

Data Index: 500627 (C4 (Web Text))

Max Activating Token Index: 653

Text #3

Max Range: 3.4098. Min Range: -3.4098

Max Act: 3.2921. Min Act: -0.1700

Data Index: 594304 (C4 (Web Text))

Max Activating Token Index: 952

Text #4

Max Range: 3.4098. Min Range: -3.4098

Max Act: 3.2822. Min Act: -0.1699

Data Index: 152501 (C4 (Web Text))

Max Activating Token Index: 497

Text #5

Max Range: 3.4098. Min Range: -3.4098

Max Act: 3.2486. Min Act: -0.1699

Data Index: 476935 (C4 (Web Text))

Max Activating Token Index: 274

Text #6

Max Range: 3.4098. Min Range: -3.4098

Max Act: 3.2284. Min Act: -0.1700

Data Index: 262078 (C4 (Web Text))

Max Activating Token Index: 894

Text #7

Max Range: 3.4098. Min Range: -3.4098

Max Act: 3.2266. Min Act: -0.1700

Data Index: 1328032 (C4 (Web Text))

Max Activating Token Index: 196

Text #8

Max Range: 3.4098. Min Range: -3.4098

Max Act: 3.2291. Min Act: -0.1700

Data Index: 1345035 (C4 (Web Text))

Max Activating Token Index: 419

Text #9

Max Range: 3.4098. Min Range: -3.4098

Max Act: 3.2159. Min Act: -0.1700

Data Index: 1271313 (C4 (Web Text))

Max Activating Token Index: 339

Text #10

Max Range: 3.4098. Min Range: -3.4098

Max Act: 3.2019. Min Act: -0.1693

Data Index: 1317774 (C4 (Web Text))

Max Activating Token Index: 142

Text #11

Max Range: 3.4098. Min Range: -3.4098

Max Act: 3.2157. Min Act: -0.1700

Data Index: 838253 (C4 (Web Text))

Max Activating Token Index: 506

Text #12

Max Range: 3.4098. Min Range: -3.4098

Max Act: 3.2205. Min Act: -0.1700

Data Index: 747238 (C4 (Web Text))

Max Activating Token Index: 553

Text #13

Max Range: 3.4098. Min Range: -3.4098

Max Act: 3.2051. Min Act: -0.1700

Data Index: 689399 (C4 (Web Text))

Max Activating Token Index: 315

Text #14

Max Range: 3.4098. Min Range: -3.4098

Max Act: 3.1807. Min Act: -0.1700

Data Index: 236305 (C4 (Web Text))

Max Activating Token Index: 143

Text #15

Max Range: 3.4098. Min Range: -3.4098

Max Act: 3.1719. Min Act: -0.1698

Data Index: 1011024 (C4 (Web Text))

Max Activating Token Index: 207

Text #16

Max Range: 3.4098. Min Range: -3.4098

Max Act: 3.1657. Min Act: -0.1700

Data Index: 638708 (C4 (Web Text))

Max Activating Token Index: 21

Text #17

Max Range: 3.4098. Min Range: -3.4098

Max Act: 3.1709. Min Act: -0.1700

Data Index: 684513 (C4 (Web Text))

Max Activating Token Index: 712

Text #18

Max Range: 3.4098. Min Range: -3.4098

Max Act: 3.1517. Min Act: -0.1699

Data Index: 785401 (C4 (Web Text))

Max Activating Token Index: 729

Text #19

Max Range: 3.4098. Min Range: -3.4098

Max Act: 3.1441. Min Act: -0.1700

Data Index: 1300220 (C4 (Web Text))

Max Activating Token Index: 517