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

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

Neuron 377 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: 3.6593. Min Range: -3.6593

Max Act: 3.6593. Min Act: -0.1700

Data Index: 95830 (C4 (Web Text))

Max Activating Token Index: 1023

Text #1

Max Range: 3.6593. Min Range: -3.6593

Max Act: 3.5340. Min Act: -0.1700

Data Index: 958226 (C4 (Web Text))

Max Activating Token Index: 417

Text #2

Max Range: 3.6593. Min Range: -3.6593

Max Act: 3.5340. Min Act: -0.1700

Data Index: 655428 (C4 (Web Text))

Max Activating Token Index: 905

Text #3

Max Range: 3.6593. Min Range: -3.6593

Max Act: 3.5340. Min Act: -0.1700

Data Index: 1207132 (C4 (Web Text))

Max Activating Token Index: 501

Text #4

Max Range: 3.6593. Min Range: -3.6593

Max Act: 3.5340. Min Act: -0.1700

Data Index: 39687 (C4 (Web Text))

Max Activating Token Index: 79

Text #5

Max Range: 3.6593. Min Range: -3.6593

Max Act: 3.4714. Min Act: -0.1700

Data Index: 617325 (C4 (Web Text))

Max Activating Token Index: 399

Text #6

Max Range: 3.6593. Min Range: -3.6593

Max Act: 3.4714. Min Act: -0.1700

Data Index: 1181711 (C4 (Web Text))

Max Activating Token Index: 1023

Text #7

Max Range: 3.6593. Min Range: -3.6593

Max Act: 3.5027. Min Act: -0.1700

Data Index: 1191305 (C4 (Web Text))

Max Activating Token Index: 474

Text #8

Max Range: 3.6593. Min Range: -3.6593

Max Act: 3.5027. Min Act: -0.1700

Data Index: 1033482 (C4 (Web Text))

Max Activating Token Index: 990

Text #9

Max Range: 3.6593. Min Range: -3.6593

Max Act: 3.4400. Min Act: -0.1700

Data Index: 1331569 (C4 (Web Text))

Max Activating Token Index: 307

Text #10

Max Range: 3.6593. Min Range: -3.6593

Max Act: 3.4400. Min Act: -0.1700

Data Index: 864774 (C4 (Web Text))

Max Activating Token Index: 175

Text #11

Max Range: 3.6593. Min Range: -3.6593

Max Act: 3.4714. Min Act: -0.1700

Data Index: 301277 (C4 (Web Text))

Max Activating Token Index: 438

Text #12

Max Range: 3.6593. Min Range: -3.6593

Max Act: 3.4400. Min Act: -0.1700

Data Index: 1055828 (C4 (Web Text))

Max Activating Token Index: 526

Text #13

Max Range: 3.6593. Min Range: -3.6593

Max Act: 3.4400. Min Act: -0.1700

Data Index: 319782 (C4 (Web Text))

Max Activating Token Index: 25

Text #14

Max Range: 3.6593. Min Range: -3.6593

Max Act: 3.4087. Min Act: -0.1700

Data Index: 627638 (C4 (Web Text))

Max Activating Token Index: 389

Text #15

Max Range: 3.6593. Min Range: -3.6593

Max Act: 3.4087. Min Act: -0.1700

Data Index: 1348195 (C4 (Web Text))

Max Activating Token Index: 985

Text #16

Max Range: 3.6593. Min Range: -3.6593

Max Act: 3.4400. Min Act: -0.1700

Data Index: 601188 (C4 (Web Text))

Max Activating Token Index: 323

Text #17

Max Range: 3.6593. Min Range: -3.6593

Max Act: 3.4087. Min Act: -0.1700

Data Index: 412562 (C4 (Web Text))

Max Activating Token Index: 398

Text #18

Max Range: 3.6593. Min Range: -3.6593

Max Act: 3.3930. Min Act: -0.1700

Data Index: 1311820 (C4 (Web Text))

Max Activating Token Index: 228

Text #19

Max Range: 3.6593. Min Range: -3.6593

Max Act: 3.3616. Min Act: -0.1700

Data Index: 1291713 (C4 (Web Text))

Max Activating Token Index: 348