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

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

Neuron 254 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.9975. Min Range: -5.9975

Max Act: 5.9975. Min Act: -0.1700

Data Index: 372678 (C4 (Web Text))

Max Activating Token Index: 665

Text #1

Max Range: 5.9975. Min Range: -5.9975

Max Act: 5.8413. Min Act: -0.1700

Data Index: 1070295 (C4 (Web Text))

Max Activating Token Index: 308

Text #2

Max Range: 5.9975. Min Range: -5.9975

Max Act: 5.8413. Min Act: -0.1700

Data Index: 538227 (C4 (Web Text))

Max Activating Token Index: 310

Text #3

Max Range: 5.9975. Min Range: -5.9975

Max Act: 5.8413. Min Act: -0.1700

Data Index: 11723 (C4 (Web Text))

Max Activating Token Index: 536

Text #4

Max Range: 5.9975. Min Range: -5.9975

Max Act: 5.8100. Min Act: -0.1700

Data Index: 248611 (C4 (Web Text))

Max Activating Token Index: 304

Text #5

Max Range: 5.9975. Min Range: -5.9975

Max Act: 5.8100. Min Act: -0.1700

Data Index: 357255 (C4 (Web Text))

Max Activating Token Index: 690

Text #6

Max Range: 5.9975. Min Range: -5.9975

Max Act: 5.7475. Min Act: -0.1700

Data Index: 350681 (C4 (Web Text))

Max Activating Token Index: 611

Text #7

Max Range: 5.9975. Min Range: -5.9975

Max Act: 5.7163. Min Act: -0.1700

Data Index: 1171544 (C4 (Web Text))

Max Activating Token Index: 576

Text #8

Max Range: 5.9975. Min Range: -5.9975

Max Act: 5.7475. Min Act: -0.1700

Data Index: 1212605 (C4 (Web Text))

Max Activating Token Index: 692

Text #9

Max Range: 5.9975. Min Range: -5.9975

Max Act: 5.7163. Min Act: -0.1700

Data Index: 843756 (C4 (Web Text))

Max Activating Token Index: 639

Text #10

Max Range: 5.9975. Min Range: -5.9975

Max Act: 5.6850. Min Act: -0.1700

Data Index: 192949 (C4 (Web Text))

Max Activating Token Index: 182

Text #11

Max Range: 5.9975. Min Range: -5.9975

Max Act: 5.6225. Min Act: -0.1700

Data Index: 77484 (C4 (Web Text))

Max Activating Token Index: 446

Text #12

Max Range: 5.9975. Min Range: -5.9975

Max Act: 5.6850. Min Act: -0.1700

Data Index: 508725 (C4 (Web Text))

Max Activating Token Index: 776

Text #13

Max Range: 5.9975. Min Range: -5.9975

Max Act: 5.6850. Min Act: -0.1700

Data Index: 32964 (C4 (Web Text))

Max Activating Token Index: 445

Text #14

Max Range: 5.9975. Min Range: -5.9975

Max Act: 5.6538. Min Act: -0.1700

Data Index: 569572 (C4 (Web Text))

Max Activating Token Index: 662

Text #15

Max Range: 5.9975. Min Range: -5.9975

Max Act: 5.6850. Min Act: -0.1700

Data Index: 1143950 (C4 (Web Text))

Max Activating Token Index: 714

Text #16

Max Range: 5.9975. Min Range: -5.9975

Max Act: 5.5600. Min Act: -0.1700

Data Index: 1217049 (C4 (Web Text))

Max Activating Token Index: 567

Text #17

Max Range: 5.9975. Min Range: -5.9975

Max Act: 5.6225. Min Act: -0.1700

Data Index: 1181495 (C4 (Web Text))

Max Activating Token Index: 632

Text #18

Max Range: 5.9975. Min Range: -5.9975

Max Act: 5.6225. Min Act: -0.1700

Data Index: 405424 (C4 (Web Text))

Max Activating Token Index: 780

Text #19

Max Range: 5.9975. Min Range: -5.9975

Max Act: 5.5913. Min Act: -0.1700

Data Index: 901402 (C4 (Web Text))

Max Activating Token Index: 327