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

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

Neuron 669 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: 4.8945. Min Range: -4.8945

Max Act: 4.8945. Min Act: -0.1700

Data Index: 1163300 (C4 (Web Text))

Max Activating Token Index: 962

Text #1

Max Range: 4.8945. Min Range: -4.8945

Max Act: 4.8284. Min Act: -0.1700

Data Index: 683928 (C4 (Web Text))

Max Activating Token Index: 527

Text #2

Max Range: 4.8945. Min Range: -4.8945

Max Act: 4.8098. Min Act: -0.1700

Data Index: 106760 (C4 (Web Text))

Max Activating Token Index: 326

Text #3

Max Range: 4.8945. Min Range: -4.8945

Max Act: 4.7172. Min Act: -0.1700

Data Index: 997173 (C4 (Web Text))

Max Activating Token Index: 466

Text #4

Max Range: 4.8945. Min Range: -4.8945

Max Act: 4.7541. Min Act: -0.1700

Data Index: 530065 (C4 (Web Text))

Max Activating Token Index: 730

Text #5

Max Range: 4.8945. Min Range: -4.8945

Max Act: 4.6263. Min Act: -0.1700

Data Index: 765837 (C4 (Web Text))

Max Activating Token Index: 279

Text #6

Max Range: 4.8945. Min Range: -4.8945

Max Act: 4.6103. Min Act: -0.1700

Data Index: 1297869 (C4 (Web Text))

Max Activating Token Index: 595

Text #7

Max Range: 4.8945. Min Range: -4.8945

Max Act: 4.6013. Min Act: -0.1700

Data Index: 356672 (C4 (Web Text))

Max Activating Token Index: 242

Text #8

Max Range: 4.8945. Min Range: -4.8945

Max Act: 4.6689. Min Act: -0.1700

Data Index: 1081784 (C4 (Web Text))

Max Activating Token Index: 967

Text #9

Max Range: 4.8945. Min Range: -4.8945

Max Act: 4.5256. Min Act: -0.1700

Data Index: 16277 (C4 (Web Text))

Max Activating Token Index: 866

Text #10

Max Range: 4.8945. Min Range: -4.8945

Max Act: 4.5600. Min Act: -0.1700

Data Index: 324414 (C4 (Web Text))

Max Activating Token Index: 475

Text #11

Max Range: 4.8945. Min Range: -4.8945

Max Act: 4.5598. Min Act: -0.1700

Data Index: 710271 (C4 (Web Text))

Max Activating Token Index: 819

Text #12

Max Range: 4.8945. Min Range: -4.8945

Max Act: 4.5561. Min Act: -0.1700

Data Index: 705519 (C4 (Web Text))

Max Activating Token Index: 397

Text #13

Max Range: 4.8945. Min Range: -4.8945

Max Act: 4.5275. Min Act: -0.1700

Data Index: 1123986 (C4 (Web Text))

Max Activating Token Index: 689

Text #14

Max Range: 4.8945. Min Range: -4.8945

Max Act: 4.5054. Min Act: -0.1700

Data Index: 794494 (C4 (Web Text))

Max Activating Token Index: 506

Text #15

Max Range: 4.8945. Min Range: -4.8945

Max Act: 4.4672. Min Act: -0.1700

Data Index: 147419 (C4 (Web Text))

Max Activating Token Index: 381

Text #16

Max Range: 4.8945. Min Range: -4.8945

Max Act: 4.4742. Min Act: -0.1700

Data Index: 1274886 (C4 (Web Text))

Max Activating Token Index: 990

Text #17

Max Range: 4.8945. Min Range: -4.8945

Max Act: 4.4283. Min Act: -0.1700

Data Index: 789588 (C4 (Web Text))

Max Activating Token Index: 156

Text #18

Max Range: 4.8945. Min Range: -4.8945

Max Act: 4.4891. Min Act: -0.1700

Data Index: 1347978 (C4 (Web Text))

Max Activating Token Index: 282

Text #19

Max Range: 4.8945. Min Range: -4.8945

Max Act: 4.4637. Min Act: -0.1700

Data Index: 165618 (C4 (Web Text))

Max Activating Token Index: 144