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

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

Neuron 650 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: 3.8505. Min Range: -3.8505

Max Act: 3.8505. Min Act: -0.1700

Data Index: 315317 (C4 (Web Text))

Max Activating Token Index: 980

Text #1

Max Range: 3.8505. Min Range: -3.8505

Max Act: 3.7530. Min Act: -0.1700

Data Index: 983214 (C4 (Web Text))

Max Activating Token Index: 622

Text #2

Max Range: 3.8505. Min Range: -3.8505

Max Act: 3.6679. Min Act: -0.1700

Data Index: 746881 (C4 (Web Text))

Max Activating Token Index: 435

Text #3

Max Range: 3.8505. Min Range: -3.8505

Max Act: 3.6380. Min Act: -0.1700

Data Index: 460311 (C4 (Web Text))

Max Activating Token Index: 608

Text #4

Max Range: 3.8505. Min Range: -3.8505

Max Act: 3.5723. Min Act: -0.1700

Data Index: 490357 (C4 (Web Text))

Max Activating Token Index: 979

Text #5

Max Range: 3.8505. Min Range: -3.8505

Max Act: 3.5719. Min Act: -0.1700

Data Index: 1280652 (C4 (Web Text))

Max Activating Token Index: 402

Text #6

Max Range: 3.8505. Min Range: -3.8505

Max Act: 3.5409. Min Act: -0.1700

Data Index: 424019 (C4 (Web Text))

Max Activating Token Index: 354

Text #7

Max Range: 3.8505. Min Range: -3.8505

Max Act: 3.5514. Min Act: -0.1700

Data Index: 692300 (C4 (Web Text))

Max Activating Token Index: 255

Text #8

Max Range: 3.8505. Min Range: -3.8505

Max Act: 3.5228. Min Act: -0.1700

Data Index: 1053769 (C4 (Web Text))

Max Activating Token Index: 138

Text #9

Max Range: 3.8505. Min Range: -3.8505

Max Act: 3.5237. Min Act: -0.1700

Data Index: 1239162 (C4 (Web Text))

Max Activating Token Index: 263

Text #10

Max Range: 3.8505. Min Range: -3.8505

Max Act: 3.4828. Min Act: -0.1700

Data Index: 704279 (C4 (Web Text))

Max Activating Token Index: 793

Text #11

Max Range: 3.8505. Min Range: -3.8505

Max Act: 3.4833. Min Act: -0.1700

Data Index: 1098447 (C4 (Web Text))

Max Activating Token Index: 845

Text #12

Max Range: 3.8505. Min Range: -3.8505

Max Act: 3.4870. Min Act: -0.1700

Data Index: 1260648 (C4 (Web Text))

Max Activating Token Index: 628

Text #13

Max Range: 3.8505. Min Range: -3.8505

Max Act: 3.4891. Min Act: -0.1700

Data Index: 100043 (C4 (Web Text))

Max Activating Token Index: 978

Text #14

Max Range: 3.8505. Min Range: -3.8505

Max Act: 3.4484. Min Act: -0.1700

Data Index: 615124 (C4 (Web Text))

Max Activating Token Index: 955

Text #15

Max Range: 3.8505. Min Range: -3.8505

Max Act: 3.4694. Min Act: -0.1700

Data Index: 205382 (C4 (Web Text))

Max Activating Token Index: 751

Text #16

Max Range: 3.8505. Min Range: -3.8505

Max Act: 3.4600. Min Act: -0.1700

Data Index: 981313 (C4 (Web Text))

Max Activating Token Index: 139

Text #17

Max Range: 3.8505. Min Range: -3.8505

Max Act: 3.4389. Min Act: -0.1700

Data Index: 591226 (C4 (Web Text))

Max Activating Token Index: 859

Text #18

Max Range: 3.8505. Min Range: -3.8505

Max Act: 3.4656. Min Act: -0.1700

Data Index: 802868 (C4 (Web Text))

Max Activating Token Index: 113

Text #19

Max Range: 3.8505. Min Range: -3.8505

Max Act: 3.4588. Min Act: -0.1700

Data Index: 13599 (C4 (Web Text))

Max Activating Token Index: 41