Model: GELU Model: 2 Layers, 2048 Neurons per Layer

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

Neuron 538 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-2l')

Text #0

Max Range: 5.4496. Min Range: -5.4496

Max Act: 5.4496. Min Act: -0.1700

Data Index: 116956 (C4 (Web Text))

Max Activating Token Index: 372

Text #1

Max Range: 5.4496. Min Range: -5.4496

Max Act: 5.4496. Min Act: -0.1700

Data Index: 200495 (C4 (Web Text))

Max Activating Token Index: 926

Text #2

Max Range: 5.4496. Min Range: -5.4496

Max Act: 5.3871. Min Act: -0.1700

Data Index: 380016 (C4 (Web Text))

Max Activating Token Index: 666

Text #3

Max Range: 5.4496. Min Range: -5.4496

Max Act: 5.3246. Min Act: -0.1700

Data Index: 574158 (C4 (Web Text))

Max Activating Token Index: 36

Text #4

Max Range: 5.4496. Min Range: -5.4496

Max Act: 5.2621. Min Act: -0.1676

Data Index: 482127 (C4 (Web Text))

Max Activating Token Index: 54

Text #5

Max Range: 5.4496. Min Range: -5.4496

Max Act: 5.2934. Min Act: -0.1700

Data Index: 585854 (C4 (Web Text))

Max Activating Token Index: 175

Text #6

Max Range: 5.4496. Min Range: -5.4496

Max Act: 5.1996. Min Act: -0.1700

Data Index: 742983 (C4 (Web Text))

Max Activating Token Index: 738

Text #7

Max Range: 5.4496. Min Range: -5.4496

Max Act: 5.1996. Min Act: -0.1700

Data Index: 355233 (C4 (Web Text))

Max Activating Token Index: 50

Text #8

Max Range: 5.4496. Min Range: -5.4496

Max Act: 5.1371. Min Act: -0.1700

Data Index: 153940 (C4 (Web Text))

Max Activating Token Index: 985

Text #9

Max Range: 5.4496. Min Range: -5.4496

Max Act: 5.1684. Min Act: -0.1700

Data Index: 581627 (C4 (Web Text))

Max Activating Token Index: 316

Text #10

Max Range: 5.4496. Min Range: -5.4496

Max Act: 5.1996. Min Act: -0.1700

Data Index: 467147 (C4 (Web Text))

Max Activating Token Index: 331

Text #11

Max Range: 5.4496. Min Range: -5.4496

Max Act: 5.1059. Min Act: -0.1700

Data Index: 549461 (C4 (Web Text))

Max Activating Token Index: 528

Text #12

Max Range: 5.4496. Min Range: -5.4496

Max Act: 5.0746. Min Act: -0.1700

Data Index: 1113096 (C4 (Web Text))

Max Activating Token Index: 534

Text #13

Max Range: 5.4496. Min Range: -5.4496

Max Act: 5.1059. Min Act: -0.1700

Data Index: 1109843 (C4 (Web Text))

Max Activating Token Index: 831

Text #14

Max Range: 5.4496. Min Range: -5.4496

Max Act: 5.0746. Min Act: -0.1700

Data Index: 112966 (C4 (Web Text))

Max Activating Token Index: 934

Text #15

Max Range: 5.4496. Min Range: -5.4496

Max Act: 5.0746. Min Act: -0.1700

Data Index: 302597 (C4 (Web Text))

Max Activating Token Index: 383

Text #16

Max Range: 5.4496. Min Range: -5.4496

Max Act: 5.1059. Min Act: -0.1700

Data Index: 1040593 (C4 (Web Text))

Max Activating Token Index: 936

Text #17

Max Range: 5.4496. Min Range: -5.4496

Max Act: 5.1371. Min Act: -0.1700

Data Index: 1204315 (C4 (Web Text))

Max Activating Token Index: 215

Text #18

Max Range: 5.4496. Min Range: -5.4496

Max Act: 5.0746. Min Act: -0.1700

Data Index: 137689 (C4 (Web Text))

Max Activating Token Index: 418

Text #19

Max Range: 5.4496. Min Range: -5.4496

Max Act: 5.0746. Min Act: -0.1700

Data Index: 1252128 (C4 (Web Text))

Max Activating Token Index: 361