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

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

Neuron 1881 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: 3.4548. Min Range: -3.4548

Max Act: 3.4548. Min Act: -0.1700

Data Index: 288152 (C4 (Web Text))

Max Activating Token Index: 580

Text #1

Max Range: 3.4548. Min Range: -3.4548

Max Act: 3.4548. Min Act: -0.1700

Data Index: 648476 (C4 (Web Text))

Max Activating Token Index: 711

Text #2

Max Range: 3.4548. Min Range: -3.4548

Max Act: 3.3136. Min Act: -0.1700

Data Index: 135947 (C4 (Web Text))

Max Activating Token Index: 664

Text #3

Max Range: 3.4548. Min Range: -3.4548

Max Act: 3.3136. Min Act: -0.1700

Data Index: 1294029 (C4 (Web Text))

Max Activating Token Index: 445

Text #4

Max Range: 3.4548. Min Range: -3.4548

Max Act: 3.2665. Min Act: -0.1700

Data Index: 699128 (C4 (Web Text))

Max Activating Token Index: 283

Text #5

Max Range: 3.4548. Min Range: -3.4548

Max Act: 3.2351. Min Act: -0.1700

Data Index: 143995 (C4 (Web Text))

Max Activating Token Index: 778

Text #6

Max Range: 3.4548. Min Range: -3.4548

Max Act: 3.2351. Min Act: -0.1700

Data Index: 1034641 (C4 (Web Text))

Max Activating Token Index: 264

Text #7

Max Range: 3.4548. Min Range: -3.4548

Max Act: 3.2036. Min Act: -0.1700

Data Index: 1239719 (C4 (Web Text))

Max Activating Token Index: 936

Text #8

Max Range: 3.4548. Min Range: -3.4548

Max Act: 3.1879. Min Act: -0.1700

Data Index: 745560 (C4 (Web Text))

Max Activating Token Index: 338

Text #9

Max Range: 3.4548. Min Range: -3.4548

Max Act: 3.1564. Min Act: -0.1700

Data Index: 1094275 (C4 (Web Text))

Max Activating Token Index: 422

Text #10

Max Range: 3.4548. Min Range: -3.4548

Max Act: 3.1564. Min Act: -0.1700

Data Index: 1111910 (C4 (Web Text))

Max Activating Token Index: 519

Text #11

Max Range: 3.4548. Min Range: -3.4548

Max Act: 3.1564. Min Act: -0.1700

Data Index: 268816 (C4 (Web Text))

Max Activating Token Index: 715

Text #12

Max Range: 3.4548. Min Range: -3.4548

Max Act: 3.1721. Min Act: -0.1700

Data Index: 196764 (C4 (Web Text))

Max Activating Token Index: 592

Text #13

Max Range: 3.4548. Min Range: -3.4548

Max Act: 3.1879. Min Act: -0.1700

Data Index: 591066 (C4 (Web Text))

Max Activating Token Index: 319

Text #14

Max Range: 3.4548. Min Range: -3.4548

Max Act: 3.2036. Min Act: -0.1700

Data Index: 713467 (C4 (Web Text))

Max Activating Token Index: 451

Text #15

Max Range: 3.4548. Min Range: -3.4548

Max Act: 3.1879. Min Act: -0.1700

Data Index: 1226703 (C4 (Web Text))

Max Activating Token Index: 199

Text #16

Max Range: 3.4548. Min Range: -3.4548

Max Act: 3.1721. Min Act: -0.1700

Data Index: 1198236 (C4 (Web Text))

Max Activating Token Index: 348

Text #17

Max Range: 3.4548. Min Range: -3.4548

Max Act: 3.1879. Min Act: -0.1700

Data Index: 1209017 (C4 (Web Text))

Max Activating Token Index: 324

Text #18

Max Range: 3.4548. Min Range: -3.4548

Max Act: 3.1721. Min Act: -0.1700

Data Index: 447859 (C4 (Web Text))

Max Activating Token Index: 471

Text #19

Max Range: 3.4548. Min Range: -3.4548

Max Act: 3.1564. Min Act: -0.1700

Data Index: 659804 (C4 (Web Text))

Max Activating Token Index: 520