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

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

Neuron 505 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: 5.7365. Min Range: -5.7365

Max Act: 5.7365. Min Act: -0.1700

Data Index: 950441 (C4 (Web Text))

Max Activating Token Index: 895

Text #1

Max Range: 5.7365. Min Range: -5.7365

Max Act: 5.6740. Min Act: -0.1700

Data Index: 385561 (C4 (Web Text))

Max Activating Token Index: 841

Text #2

Max Range: 5.7365. Min Range: -5.7365

Max Act: 5.5490. Min Act: -0.1700

Data Index: 1298063 (C4 (Web Text))

Max Activating Token Index: 643

Text #3

Max Range: 5.7365. Min Range: -5.7365

Max Act: 5.6115. Min Act: -0.1700

Data Index: 31898 (C4 (Web Text))

Max Activating Token Index: 268

Text #4

Max Range: 5.7365. Min Range: -5.7365

Max Act: 5.5803. Min Act: -0.1700

Data Index: 965305 (C4 (Web Text))

Max Activating Token Index: 18

Text #5

Max Range: 5.7365. Min Range: -5.7365

Max Act: 5.5490. Min Act: -0.1700

Data Index: 193482 (C4 (Web Text))

Max Activating Token Index: 387

Text #6

Max Range: 5.7365. Min Range: -5.7365

Max Act: 5.5178. Min Act: -0.1700

Data Index: 1278474 (C4 (Web Text))

Max Activating Token Index: 573

Text #7

Max Range: 5.7365. Min Range: -5.7365

Max Act: 5.4865. Min Act: -0.1699

Data Index: 1124427 (C4 (Web Text))

Max Activating Token Index: 737

Text #8

Max Range: 5.7365. Min Range: -5.7365

Max Act: 5.4553. Min Act: -0.1700

Data Index: 390603 (C4 (Web Text))

Max Activating Token Index: 1015

Text #9

Max Range: 5.7365. Min Range: -5.7365

Max Act: 5.4865. Min Act: -0.1700

Data Index: 1237596 (C4 (Web Text))

Max Activating Token Index: 502

Text #10

Max Range: 5.7365. Min Range: -5.7365

Max Act: 5.3928. Min Act: -0.1700

Data Index: 1328985 (C4 (Web Text))

Max Activating Token Index: 297

Text #11

Max Range: 5.7365. Min Range: -5.7365

Max Act: 5.4553. Min Act: -0.1700

Data Index: 24924 (C4 (Web Text))

Max Activating Token Index: 702

Text #12

Max Range: 5.7365. Min Range: -5.7365

Max Act: 5.3615. Min Act: -0.1699

Data Index: 60442 (C4 (Web Text))

Max Activating Token Index: 303

Text #13

Max Range: 5.7365. Min Range: -5.7365

Max Act: 5.3928. Min Act: -0.1700

Data Index: 627961 (C4 (Web Text))

Max Activating Token Index: 411

Text #14

Max Range: 5.7365. Min Range: -5.7365

Max Act: 5.3615. Min Act: -0.1700

Data Index: 251295 (C4 (Web Text))

Max Activating Token Index: 228

Text #15

Max Range: 5.7365. Min Range: -5.7365

Max Act: 5.3303. Min Act: -0.1700

Data Index: 1359186 (C4 (Web Text))

Max Activating Token Index: 893

Text #16

Max Range: 5.7365. Min Range: -5.7365

Max Act: 5.3615. Min Act: -0.1700

Data Index: 1122327 (C4 (Web Text))

Max Activating Token Index: 152

Text #17

Max Range: 5.7365. Min Range: -5.7365

Max Act: 5.2990. Min Act: -0.1700

Data Index: 1280916 (C4 (Web Text))

Max Activating Token Index: 373

Text #18

Max Range: 5.7365. Min Range: -5.7365

Max Act: 5.3303. Min Act: -0.1700

Data Index: 824945 (C4 (Web Text))

Max Activating Token Index: 138

Text #19

Max Range: 5.7365. Min Range: -5.7365

Max Act: 5.3615. Min Act: -0.1700

Data Index: 1008545 (C4 (Web Text))

Max Activating Token Index: 409