Model: GELU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 1713 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')

Text #0

Max Range: 3.4931. Min Range: -3.4931

Max Act: 3.4931. Min Act: -0.1700

Data Index: 150260 (C4 (Web Text))

Max Activating Token Index: 635

Text #1

Max Range: 3.4931. Min Range: -3.4931

Max Act: 3.4461. Min Act: -0.1700

Data Index: 229465 (C4 (Web Text))

Max Activating Token Index: 161

Text #2

Max Range: 3.4931. Min Range: -3.4931

Max Act: 3.3520. Min Act: -0.1700

Data Index: 152175 (C4 (Web Text))

Max Activating Token Index: 418

Text #3

Max Range: 3.4931. Min Range: -3.4931

Max Act: 3.3834. Min Act: -0.1700

Data Index: 382096 (C4 (Web Text))

Max Activating Token Index: 169

Text #4

Max Range: 3.4931. Min Range: -3.4931

Max Act: 3.4147. Min Act: -0.1700

Data Index: 1068649 (C4 (Web Text))

Max Activating Token Index: 976

Text #5

Max Range: 3.4931. Min Range: -3.4931

Max Act: 3.3363. Min Act: -0.1700

Data Index: 1079938 (C4 (Web Text))

Max Activating Token Index: 970

Text #6

Max Range: 3.4931. Min Range: -3.4931

Max Act: 3.3363. Min Act: -0.1700

Data Index: 318950 (C4 (Web Text))

Max Activating Token Index: 389

Text #7

Max Range: 3.4931. Min Range: -3.4931

Max Act: 3.3520. Min Act: -0.1700

Data Index: 507651 (C4 (Web Text))

Max Activating Token Index: 370

Text #8

Max Range: 3.4931. Min Range: -3.4931

Max Act: 3.3206. Min Act: -0.1700

Data Index: 896690 (C4 (Web Text))

Max Activating Token Index: 649

Text #9

Max Range: 3.4931. Min Range: -3.4931

Max Act: 3.3363. Min Act: -0.1700

Data Index: 529042 (C4 (Web Text))

Max Activating Token Index: 569

Text #10

Max Range: 3.4931. Min Range: -3.4931

Max Act: 3.3206. Min Act: -0.1700

Data Index: 833200 (C4 (Web Text))

Max Activating Token Index: 568

Text #11

Max Range: 3.4931. Min Range: -3.4931

Max Act: 3.2892. Min Act: -0.1700

Data Index: 314005 (C4 (Web Text))

Max Activating Token Index: 601

Text #12

Max Range: 3.4931. Min Range: -3.4931

Max Act: 3.3049. Min Act: -0.1700

Data Index: 1274363 (C4 (Web Text))

Max Activating Token Index: 356

Text #13

Max Range: 3.4931. Min Range: -3.4931

Max Act: 3.2892. Min Act: -0.1700

Data Index: 888734 (C4 (Web Text))

Max Activating Token Index: 408

Text #14

Max Range: 3.4931. Min Range: -3.4931

Max Act: 3.2263. Min Act: -0.1700

Data Index: 1063195 (C4 (Web Text))

Max Activating Token Index: 654

Text #15

Max Range: 3.4931. Min Range: -3.4931

Max Act: 3.2892. Min Act: -0.1700

Data Index: 718520 (C4 (Web Text))

Max Activating Token Index: 565

Text #16

Max Range: 3.4931. Min Range: -3.4931

Max Act: 3.2263. Min Act: -0.1700

Data Index: 1229663 (C4 (Web Text))

Max Activating Token Index: 479

Text #17

Max Range: 3.4931. Min Range: -3.4931

Max Act: 3.2735. Min Act: -0.1700

Data Index: 872593 (C4 (Web Text))

Max Activating Token Index: 267

Text #18

Max Range: 3.4931. Min Range: -3.4931

Max Act: 3.2735. Min Act: -0.1700

Data Index: 351230 (C4 (Web Text))

Max Activating Token Index: 661

Text #19

Max Range: 3.4931. Min Range: -3.4931

Max Act: 3.2735. Min Act: -0.1700

Data Index: 1155597 (C4 (Web Text))

Max Activating Token Index: 370