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

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

Neuron 335 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: 5.3880. Min Range: -5.3880

Max Act: 5.3880. Min Act: -0.1700

Data Index: 483722 (C4 (Web Text))

Max Activating Token Index: 950

Text #1

Max Range: 5.3880. Min Range: -5.3880

Max Act: 5.1692. Min Act: -0.1700

Data Index: 495858 (C4 (Web Text))

Max Activating Token Index: 278

Text #2

Max Range: 5.3880. Min Range: -5.3880

Max Act: 5.2630. Min Act: -0.1700

Data Index: 325573 (C4 (Web Text))

Max Activating Token Index: 374

Text #3

Max Range: 5.3880. Min Range: -5.3880

Max Act: 5.1692. Min Act: -0.1700

Data Index: 268733 (C4 (Web Text))

Max Activating Token Index: 291

Text #4

Max Range: 5.3880. Min Range: -5.3880

Max Act: 5.2317. Min Act: -0.1700

Data Index: 1228539 (C4 (Web Text))

Max Activating Token Index: 150

Text #5

Max Range: 5.3880. Min Range: -5.3880

Max Act: 5.2942. Min Act: -0.1700

Data Index: 80434 (C4 (Web Text))

Max Activating Token Index: 659

Text #6

Max Range: 5.3880. Min Range: -5.3880

Max Act: 5.1692. Min Act: -0.1700

Data Index: 1040301 (C4 (Web Text))

Max Activating Token Index: 566

Text #7

Max Range: 5.3880. Min Range: -5.3880

Max Act: 5.1067. Min Act: -0.1700

Data Index: 7645 (C4 (Web Text))

Max Activating Token Index: 1013

Text #8

Max Range: 5.3880. Min Range: -5.3880

Max Act: 5.0755. Min Act: -0.1700

Data Index: 369896 (C4 (Web Text))

Max Activating Token Index: 636

Text #9

Max Range: 5.3880. Min Range: -5.3880

Max Act: 5.0755. Min Act: -0.1700

Data Index: 512466 (C4 (Web Text))

Max Activating Token Index: 667

Text #10

Max Range: 5.3880. Min Range: -5.3880

Max Act: 5.0442. Min Act: -0.1700

Data Index: 121889 (C4 (Web Text))

Max Activating Token Index: 344

Text #11

Max Range: 5.3880. Min Range: -5.3880

Max Act: 5.0755. Min Act: -0.1700

Data Index: 251892 (C4 (Web Text))

Max Activating Token Index: 98

Text #12

Max Range: 5.3880. Min Range: -5.3880

Max Act: 5.0755. Min Act: -0.1700

Data Index: 534775 (C4 (Web Text))

Max Activating Token Index: 800

Text #13

Max Range: 5.3880. Min Range: -5.3880

Max Act: 5.0755. Min Act: -0.1699

Data Index: 383663 (C4 (Web Text))

Max Activating Token Index: 587

Text #14

Max Range: 5.3880. Min Range: -5.3880

Max Act: 5.0755. Min Act: -0.1700

Data Index: 652194 (C4 (Web Text))

Max Activating Token Index: 787

Text #15

Max Range: 5.3880. Min Range: -5.3880

Max Act: 5.0130. Min Act: -0.1700

Data Index: 287884 (C4 (Web Text))

Max Activating Token Index: 729

Text #16

Max Range: 5.3880. Min Range: -5.3880

Max Act: 4.9817. Min Act: -0.1700

Data Index: 1146276 (C4 (Web Text))

Max Activating Token Index: 34

Text #17

Max Range: 5.3880. Min Range: -5.3880

Max Act: 5.0130. Min Act: -0.1700

Data Index: 138927 (C4 (Web Text))

Max Activating Token Index: 951

Text #18

Max Range: 5.3880. Min Range: -5.3880

Max Act: 4.9192. Min Act: -0.1700

Data Index: 734179 (C4 (Web Text))

Max Activating Token Index: 285

Text #19

Max Range: 5.3880. Min Range: -5.3880

Max Act: 4.9505. Min Act: -0.1700

Data Index: 625465 (C4 (Web Text))

Max Activating Token Index: 602