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

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

Neuron 565 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: 3.5847. Min Range: -3.5847

Max Act: 3.5847. Min Act: -0.1700

Data Index: 1250623 (C4 (Web Text))

Max Activating Token Index: 697

Text #1

Max Range: 3.5847. Min Range: -3.5847

Max Act: 3.4750. Min Act: -0.1700

Data Index: 742595 (C4 (Web Text))

Max Activating Token Index: 913

Text #2

Max Range: 3.5847. Min Range: -3.5847

Max Act: 3.5220. Min Act: -0.1700

Data Index: 923522 (C4 (Web Text))

Max Activating Token Index: 788

Text #3

Max Range: 3.5847. Min Range: -3.5847

Max Act: 3.4593. Min Act: -0.1700

Data Index: 1137005 (C4 (Web Text))

Max Activating Token Index: 340

Text #4

Max Range: 3.5847. Min Range: -3.5847

Max Act: 3.4280. Min Act: -0.1700

Data Index: 723116 (C4 (Web Text))

Max Activating Token Index: 391

Text #5

Max Range: 3.5847. Min Range: -3.5847

Max Act: 3.4123. Min Act: -0.1700

Data Index: 443491 (C4 (Web Text))

Max Activating Token Index: 261

Text #6

Max Range: 3.5847. Min Range: -3.5847

Max Act: 3.4437. Min Act: -0.1700

Data Index: 404532 (C4 (Web Text))

Max Activating Token Index: 719

Text #7

Max Range: 3.5847. Min Range: -3.5847

Max Act: 3.3652. Min Act: -0.1700

Data Index: 1251449 (C4 (Web Text))

Max Activating Token Index: 518

Text #8

Max Range: 3.5847. Min Range: -3.5847

Max Act: 3.4280. Min Act: -0.1700

Data Index: 179189 (C4 (Web Text))

Max Activating Token Index: 577

Text #9

Max Range: 3.5847. Min Range: -3.5847

Max Act: 3.4123. Min Act: -0.1700

Data Index: 506214 (C4 (Web Text))

Max Activating Token Index: 536

Text #10

Max Range: 3.5847. Min Range: -3.5847

Max Act: 3.3652. Min Act: -0.1700

Data Index: 612076 (C4 (Web Text))

Max Activating Token Index: 138

Text #11

Max Range: 3.5847. Min Range: -3.5847

Max Act: 3.3966. Min Act: -0.1700

Data Index: 844118 (C4 (Web Text))

Max Activating Token Index: 536

Text #12

Max Range: 3.5847. Min Range: -3.5847

Max Act: 3.3809. Min Act: -0.1700

Data Index: 1129083 (C4 (Web Text))

Max Activating Token Index: 727

Text #13

Max Range: 3.5847. Min Range: -3.5847

Max Act: 3.3181. Min Act: -0.1700

Data Index: 125065 (C4 (Web Text))

Max Activating Token Index: 286

Text #14

Max Range: 3.5847. Min Range: -3.5847

Max Act: 3.3024. Min Act: -0.1700

Data Index: 247389 (C4 (Web Text))

Max Activating Token Index: 284

Text #15

Max Range: 3.5847. Min Range: -3.5847

Max Act: 3.3652. Min Act: -0.1700

Data Index: 159387 (C4 (Web Text))

Max Activating Token Index: 655

Text #16

Max Range: 3.5847. Min Range: -3.5847

Max Act: 3.3024. Min Act: -0.1700

Data Index: 461753 (C4 (Web Text))

Max Activating Token Index: 173

Text #17

Max Range: 3.5847. Min Range: -3.5847

Max Act: 3.2081. Min Act: -0.1700

Data Index: 363066 (C4 (Web Text))

Max Activating Token Index: 295

Text #18

Max Range: 3.5847. Min Range: -3.5847

Max Act: 3.3024. Min Act: -0.1700

Data Index: 997689 (C4 (Web Text))

Max Activating Token Index: 905

Text #19

Max Range: 3.5847. Min Range: -3.5847

Max Act: 3.2239. Min Act: -0.1700

Data Index: 896181 (C4 (Web Text))

Max Activating Token Index: 676