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

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

Neuron 291 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: 5.4273. Min Range: -5.4273

Max Act: 5.4273. Min Act: -0.1700

Data Index: 681062 (C4 (Web Text))

Max Activating Token Index: 382

Text #1

Max Range: 5.4273. Min Range: -5.4273

Max Act: 5.1461. Min Act: -0.1700

Data Index: 310998 (C4 (Web Text))

Max Activating Token Index: 390

Text #2

Max Range: 5.4273. Min Range: -5.4273

Max Act: 5.1148. Min Act: -0.1700

Data Index: 536230 (C4 (Web Text))

Max Activating Token Index: 155

Text #3

Max Range: 5.4273. Min Range: -5.4273

Max Act: 5.1773. Min Act: -0.1700

Data Index: 898958 (C4 (Web Text))

Max Activating Token Index: 130

Text #4

Max Range: 5.4273. Min Range: -5.4273

Max Act: 5.0211. Min Act: -0.1700

Data Index: 1305587 (C4 (Web Text))

Max Activating Token Index: 740

Text #5

Max Range: 5.4273. Min Range: -5.4273

Max Act: 5.0836. Min Act: -0.1700

Data Index: 1353591 (C4 (Web Text))

Max Activating Token Index: 557

Text #6

Max Range: 5.4273. Min Range: -5.4273

Max Act: 5.0211. Min Act: -0.1700

Data Index: 553636 (C4 (Web Text))

Max Activating Token Index: 560

Text #7

Max Range: 5.4273. Min Range: -5.4273

Max Act: 5.0523. Min Act: -0.1700

Data Index: 855772 (C4 (Web Text))

Max Activating Token Index: 302

Text #8

Max Range: 5.4273. Min Range: -5.4273

Max Act: 4.9898. Min Act: -0.1700

Data Index: 637432 (C4 (Web Text))

Max Activating Token Index: 323

Text #9

Max Range: 5.4273. Min Range: -5.4273

Max Act: 4.9586. Min Act: -0.1700

Data Index: 1330341 (C4 (Web Text))

Max Activating Token Index: 741

Text #10

Max Range: 5.4273. Min Range: -5.4273

Max Act: 4.9586. Min Act: -0.1700

Data Index: 1355987 (C4 (Web Text))

Max Activating Token Index: 943

Text #11

Max Range: 5.4273. Min Range: -5.4273

Max Act: 4.9586. Min Act: -0.1700

Data Index: 1288681 (C4 (Web Text))

Max Activating Token Index: 1009

Text #12

Max Range: 5.4273. Min Range: -5.4273

Max Act: 4.9586. Min Act: -0.1700

Data Index: 615710 (C4 (Web Text))

Max Activating Token Index: 607

Text #13

Max Range: 5.4273. Min Range: -5.4273

Max Act: 4.9898. Min Act: -0.1700

Data Index: 880369 (C4 (Web Text))

Max Activating Token Index: 842

Text #14

Max Range: 5.4273. Min Range: -5.4273

Max Act: 4.9586. Min Act: -0.1700

Data Index: 714127 (C4 (Web Text))

Max Activating Token Index: 405

Text #15

Max Range: 5.4273. Min Range: -5.4273

Max Act: 4.9273. Min Act: -0.1700

Data Index: 813936 (C4 (Web Text))

Max Activating Token Index: 391

Text #16

Max Range: 5.4273. Min Range: -5.4273

Max Act: 4.9586. Min Act: -0.1700

Data Index: 25645 (C4 (Web Text))

Max Activating Token Index: 602

Text #17

Max Range: 5.4273. Min Range: -5.4273

Max Act: 4.8961. Min Act: -0.1700

Data Index: 382953 (C4 (Web Text))

Max Activating Token Index: 584

Text #18

Max Range: 5.4273. Min Range: -5.4273

Max Act: 4.8961. Min Act: -0.1700

Data Index: 86734 (C4 (Web Text))

Max Activating Token Index: 691

Text #19

Max Range: 5.4273. Min Range: -5.4273

Max Act: 4.8961. Min Act: -0.1700

Data Index: 33966 (C4 (Web Text))

Max Activating Token Index: 899