Model: GELU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 910 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-3l')

Text #0

Max Range: 3.6902. Min Range: -3.6902

Max Act: 3.6902. Min Act: -0.1700

Data Index: 709364 (C4 (Web Text))

Max Activating Token Index: 142

Text #1

Max Range: 3.6902. Min Range: -3.6902

Max Act: 3.5963. Min Act: -0.1700

Data Index: 1150774 (C4 (Web Text))

Max Activating Token Index: 913

Text #2

Max Range: 3.6902. Min Range: -3.6902

Max Act: 3.4396. Min Act: -0.1700

Data Index: 990480 (C4 (Web Text))

Max Activating Token Index: 936

Text #3

Max Range: 3.6902. Min Range: -3.6902

Max Act: 3.4396. Min Act: -0.1698

Data Index: 957042 (C4 (Web Text))

Max Activating Token Index: 218

Text #4

Max Range: 3.6902. Min Range: -3.6902

Max Act: 3.4083. Min Act: -0.1696

Data Index: 1190875 (C4 (Web Text))

Max Activating Token Index: 1006

Text #5

Max Range: 3.6902. Min Range: -3.6902

Max Act: 3.4083. Min Act: -0.1700

Data Index: 489497 (C4 (Web Text))

Max Activating Token Index: 1005

Text #6

Max Range: 3.6902. Min Range: -3.6902

Max Act: 3.4083. Min Act: -0.1700

Data Index: 43738 (C4 (Web Text))

Max Activating Token Index: 255

Text #7

Max Range: 3.6902. Min Range: -3.6902

Max Act: 3.4083. Min Act: -0.1700

Data Index: 339453 (C4 (Web Text))

Max Activating Token Index: 864

Text #8

Max Range: 3.6902. Min Range: -3.6902

Max Act: 3.3141. Min Act: -0.1700

Data Index: 655811 (C4 (Web Text))

Max Activating Token Index: 418

Text #9

Max Range: 3.6902. Min Range: -3.6902

Max Act: 3.3769. Min Act: -0.1700

Data Index: 395392 (C4 (Web Text))

Max Activating Token Index: 73

Text #10

Max Range: 3.6902. Min Range: -3.6902

Max Act: 3.3769. Min Act: -0.1700

Data Index: 94850 (C4 (Web Text))

Max Activating Token Index: 669

Text #11

Max Range: 3.6902. Min Range: -3.6902

Max Act: 3.3769. Min Act: -0.1700

Data Index: 498922 (C4 (Web Text))

Max Activating Token Index: 330

Text #12

Max Range: 3.6902. Min Range: -3.6902

Max Act: 3.3141. Min Act: -0.1699

Data Index: 828114 (C4 (Web Text))

Max Activating Token Index: 944

Text #13

Max Range: 3.6902. Min Range: -3.6902

Max Act: 3.3141. Min Act: -0.1700

Data Index: 607116 (C4 (Web Text))

Max Activating Token Index: 299

Text #14

Max Range: 3.6902. Min Range: -3.6902

Max Act: 3.3141. Min Act: -0.1700

Data Index: 418201 (C4 (Web Text))

Max Activating Token Index: 120

Text #15

Max Range: 3.6902. Min Range: -3.6902

Max Act: 3.2827. Min Act: -0.1700

Data Index: 1218602 (C4 (Web Text))

Max Activating Token Index: 129

Text #16

Max Range: 3.6902. Min Range: -3.6902

Max Act: 3.3141. Min Act: -0.1700

Data Index: 265455 (C4 (Web Text))

Max Activating Token Index: 231

Text #17

Max Range: 3.6902. Min Range: -3.6902

Max Act: 3.3141. Min Act: -0.1700

Data Index: 816276 (C4 (Web Text))

Max Activating Token Index: 683

Text #18

Max Range: 3.6902. Min Range: -3.6902

Max Act: 3.2827. Min Act: -0.1700

Data Index: 891691 (C4 (Web Text))

Max Activating Token Index: 660

Text #19

Max Range: 3.6902. Min Range: -3.6902

Max Act: 3.2513. Min Act: -0.1700

Data Index: 349498 (C4 (Web Text))

Max Activating Token Index: 636