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

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

Neuron 532 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: 3.3133. Min Range: -3.3133

Max Act: 3.3133. Min Act: -0.1700

Data Index: 422355 (C4 (Web Text))

Max Activating Token Index: 709

Text #1

Max Range: 3.3133. Min Range: -3.3133

Max Act: 3.2976. Min Act: -0.1700

Data Index: 1079910 (C4 (Web Text))

Max Activating Token Index: 348

Text #2

Max Range: 3.3133. Min Range: -3.3133

Max Act: 3.2819. Min Act: -0.1700

Data Index: 1187090 (C4 (Web Text))

Max Activating Token Index: 486

Text #3

Max Range: 3.3133. Min Range: -3.3133

Max Act: 3.2819. Min Act: -0.1700

Data Index: 1203123 (C4 (Web Text))

Max Activating Token Index: 765

Text #4

Max Range: 3.3133. Min Range: -3.3133

Max Act: 3.2348. Min Act: -0.1700

Data Index: 667474 (C4 (Web Text))

Max Activating Token Index: 345

Text #5

Max Range: 3.3133. Min Range: -3.3133

Max Act: 3.2190. Min Act: -0.1700

Data Index: 640880 (C4 (Web Text))

Max Activating Token Index: 493

Text #6

Max Range: 3.3133. Min Range: -3.3133

Max Act: 3.2348. Min Act: -0.1700

Data Index: 363921 (C4 (Web Text))

Max Activating Token Index: 627

Text #7

Max Range: 3.3133. Min Range: -3.3133

Max Act: 3.2505. Min Act: -0.1700

Data Index: 898322 (C4 (Web Text))

Max Activating Token Index: 700

Text #8

Max Range: 3.3133. Min Range: -3.3133

Max Act: 3.1876. Min Act: -0.1700

Data Index: 999635 (C4 (Web Text))

Max Activating Token Index: 441

Text #9

Max Range: 3.3133. Min Range: -3.3133

Max Act: 3.1718. Min Act: -0.1700

Data Index: 564900 (C4 (Web Text))

Max Activating Token Index: 465

Text #10

Max Range: 3.3133. Min Range: -3.3133

Max Act: 3.2033. Min Act: -0.1700

Data Index: 1262281 (C4 (Web Text))

Max Activating Token Index: 615

Text #11

Max Range: 3.3133. Min Range: -3.3133

Max Act: 3.1561. Min Act: -0.1700

Data Index: 715914 (C4 (Web Text))

Max Activating Token Index: 499

Text #12

Max Range: 3.3133. Min Range: -3.3133

Max Act: 3.1403. Min Act: -0.1700

Data Index: 270613 (C4 (Web Text))

Max Activating Token Index: 1001

Text #13

Max Range: 3.3133. Min Range: -3.3133

Max Act: 3.1246. Min Act: -0.1700

Data Index: 977989 (C4 (Web Text))

Max Activating Token Index: 772

Text #14

Max Range: 3.3133. Min Range: -3.3133

Max Act: 3.1088. Min Act: -0.1700

Data Index: 48393 (C4 (Web Text))

Max Activating Token Index: 712

Text #15

Max Range: 3.3133. Min Range: -3.3133

Max Act: 3.1246. Min Act: -0.1700

Data Index: 1166939 (C4 (Web Text))

Max Activating Token Index: 803

Text #16

Max Range: 3.3133. Min Range: -3.3133

Max Act: 3.1561. Min Act: -0.1700

Data Index: 1097951 (C4 (Web Text))

Max Activating Token Index: 955

Text #17

Max Range: 3.3133. Min Range: -3.3133

Max Act: 3.0931. Min Act: -0.1700

Data Index: 663643 (C4 (Web Text))

Max Activating Token Index: 713

Text #18

Max Range: 3.3133. Min Range: -3.3133

Max Act: 3.1246. Min Act: -0.1700

Data Index: 568649 (C4 (Web Text))

Max Activating Token Index: 490

Text #19

Max Range: 3.3133. Min Range: -3.3133

Max Act: 3.0931. Min Act: -0.1700

Data Index: 780810 (C4 (Web Text))

Max Activating Token Index: 435