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

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

Neuron 1447 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.6631. Min Range: -3.6631

Max Act: 3.6631. Min Act: -0.1700

Data Index: 373369 (C4 (Web Text))

Max Activating Token Index: 158

Text #1

Max Range: 3.6631. Min Range: -3.6631

Max Act: 3.6318. Min Act: -0.1700

Data Index: 266544 (C4 (Web Text))

Max Activating Token Index: 339

Text #2

Max Range: 3.6631. Min Range: -3.6631

Max Act: 3.6005. Min Act: -0.1700

Data Index: 489027 (C4 (Web Text))

Max Activating Token Index: 132

Text #3

Max Range: 3.6631. Min Range: -3.6631

Max Act: 3.5692. Min Act: -0.1700

Data Index: 749413 (C4 (Web Text))

Max Activating Token Index: 917

Text #4

Max Range: 3.6631. Min Range: -3.6631

Max Act: 3.5848. Min Act: -0.1700

Data Index: 12313 (C4 (Web Text))

Max Activating Token Index: 317

Text #5

Max Range: 3.6631. Min Range: -3.6631

Max Act: 3.5692. Min Act: -0.1700

Data Index: 1314950 (C4 (Web Text))

Max Activating Token Index: 5

Text #6

Max Range: 3.6631. Min Range: -3.6631

Max Act: 3.5692. Min Act: -0.1700

Data Index: 477140 (C4 (Web Text))

Max Activating Token Index: 188

Text #7

Max Range: 3.6631. Min Range: -3.6631

Max Act: 3.5692. Min Act: -0.1700

Data Index: 1263951 (C4 (Web Text))

Max Activating Token Index: 584

Text #8

Max Range: 3.6631. Min Range: -3.6631

Max Act: 3.5535. Min Act: -0.1700

Data Index: 863323 (C4 (Web Text))

Max Activating Token Index: 295

Text #9

Max Range: 3.6631. Min Range: -3.6631

Max Act: 3.5378. Min Act: -0.1700

Data Index: 747068 (C4 (Web Text))

Max Activating Token Index: 3

Text #10

Max Range: 3.6631. Min Range: -3.6631

Max Act: 3.5222. Min Act: -0.1700

Data Index: 907477 (C4 (Web Text))

Max Activating Token Index: 398

Text #11

Max Range: 3.6631. Min Range: -3.6631

Max Act: 3.5378. Min Act: -0.1700

Data Index: 42947 (C4 (Web Text))

Max Activating Token Index: 447

Text #12

Max Range: 3.6631. Min Range: -3.6631

Max Act: 3.5222. Min Act: -0.1700

Data Index: 31333 (C4 (Web Text))

Max Activating Token Index: 310

Text #13

Max Range: 3.6631. Min Range: -3.6631

Max Act: 3.5222. Min Act: -0.1700

Data Index: 524306 (C4 (Web Text))

Max Activating Token Index: 2

Text #14

Max Range: 3.6631. Min Range: -3.6631

Max Act: 3.5222. Min Act: -0.1700

Data Index: 566493 (C4 (Web Text))

Max Activating Token Index: 4

Text #15

Max Range: 3.6631. Min Range: -3.6631

Max Act: 3.5222. Min Act: -0.1700

Data Index: 580674 (C4 (Web Text))

Max Activating Token Index: 2

Text #16

Max Range: 3.6631. Min Range: -3.6631

Max Act: 3.5378. Min Act: -0.1700

Data Index: 358317 (C4 (Web Text))

Max Activating Token Index: 327

Text #17

Max Range: 3.6631. Min Range: -3.6631

Max Act: 3.5222. Min Act: -0.1700

Data Index: 1286120 (C4 (Web Text))

Max Activating Token Index: 2

Text #18

Max Range: 3.6631. Min Range: -3.6631

Max Act: 3.5065. Min Act: -0.1700

Data Index: 276419 (C4 (Web Text))

Max Activating Token Index: 847

Text #19

Max Range: 3.6631. Min Range: -3.6631

Max Act: 3.5065. Min Act: -0.1700

Data Index: 460758 (C4 (Web Text))

Max Activating Token Index: 4