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

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

Neuron 1625 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: 3.1631. Min Range: -3.1631

Max Act: 3.1631. Min Act: -0.1700

Data Index: 1289969 (C4 (Web Text))

Max Activating Token Index: 503

Text #1

Max Range: 3.1631. Min Range: -3.1631

Max Act: 3.1631. Min Act: -0.1700

Data Index: 920138 (C4 (Web Text))

Max Activating Token Index: 691

Text #2

Max Range: 3.1631. Min Range: -3.1631

Max Act: 3.1158. Min Act: -0.1700

Data Index: 712079 (C4 (Web Text))

Max Activating Token Index: 635

Text #3

Max Range: 3.1631. Min Range: -3.1631

Max Act: 3.0685. Min Act: -0.1700

Data Index: 713908 (C4 (Web Text))

Max Activating Token Index: 596

Text #4

Max Range: 3.1631. Min Range: -3.1631

Max Act: 3.0211. Min Act: -0.1700

Data Index: 1077017 (C4 (Web Text))

Max Activating Token Index: 650

Text #5

Max Range: 3.1631. Min Range: -3.1631

Max Act: 3.0369. Min Act: -0.1700

Data Index: 41896 (C4 (Web Text))

Max Activating Token Index: 711

Text #6

Max Range: 3.1631. Min Range: -3.1631

Max Act: 3.0685. Min Act: -0.1700

Data Index: 495053 (C4 (Web Text))

Max Activating Token Index: 482

Text #7

Max Range: 3.1631. Min Range: -3.1631

Max Act: 3.1001. Min Act: -0.1700

Data Index: 708321 (C4 (Web Text))

Max Activating Token Index: 195

Text #8

Max Range: 3.1631. Min Range: -3.1631

Max Act: 3.0685. Min Act: -0.1700

Data Index: 32403 (C4 (Web Text))

Max Activating Token Index: 564

Text #9

Max Range: 3.1631. Min Range: -3.1631

Max Act: 3.0527. Min Act: -0.1700

Data Index: 819935 (C4 (Web Text))

Max Activating Token Index: 334

Text #10

Max Range: 3.1631. Min Range: -3.1631

Max Act: 3.0527. Min Act: -0.1700

Data Index: 904720 (C4 (Web Text))

Max Activating Token Index: 582

Text #11

Max Range: 3.1631. Min Range: -3.1631

Max Act: 3.0527. Min Act: -0.1700

Data Index: 800878 (C4 (Web Text))

Max Activating Token Index: 459

Text #12

Max Range: 3.1631. Min Range: -3.1631

Max Act: 3.0527. Min Act: -0.1700

Data Index: 1295167 (C4 (Web Text))

Max Activating Token Index: 562

Text #13

Max Range: 3.1631. Min Range: -3.1631

Max Act: 3.0211. Min Act: -0.1700

Data Index: 884562 (C4 (Web Text))

Max Activating Token Index: 608

Text #14

Max Range: 3.1631. Min Range: -3.1631

Max Act: 3.0527. Min Act: -0.1700

Data Index: 457793 (C4 (Web Text))

Max Activating Token Index: 190

Text #15

Max Range: 3.1631. Min Range: -3.1631

Max Act: 3.0527. Min Act: -0.1700

Data Index: 534899 (C4 (Web Text))

Max Activating Token Index: 735

Text #16

Max Range: 3.1631. Min Range: -3.1631

Max Act: 3.0527. Min Act: -0.1700

Data Index: 528192 (C4 (Web Text))

Max Activating Token Index: 749

Text #17

Max Range: 3.1631. Min Range: -3.1631

Max Act: 3.0211. Min Act: -0.1700

Data Index: 304511 (C4 (Web Text))

Max Activating Token Index: 197

Text #18

Max Range: 3.1631. Min Range: -3.1631

Max Act: 3.0369. Min Act: -0.1700

Data Index: 1107882 (C4 (Web Text))

Max Activating Token Index: 741

Text #19

Max Range: 3.1631. Min Range: -3.1631

Max Act: 3.0369. Min Act: -0.1700

Data Index: 1086094 (C4 (Web Text))

Max Activating Token Index: 664