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

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

Neuron 1646 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: 5.8408. Min Range: -5.8408

Max Act: 5.8408. Min Act: -0.1700

Data Index: 29505 (C4 (Web Text))

Max Activating Token Index: 752

Text #1

Max Range: 5.8408. Min Range: -5.8408

Max Act: 5.6845. Min Act: -0.1700

Data Index: 337664 (C4 (Web Text))

Max Activating Token Index: 341

Text #2

Max Range: 5.8408. Min Range: -5.8408

Max Act: 5.5283. Min Act: -0.1700

Data Index: 921183 (C4 (Web Text))

Max Activating Token Index: 518

Text #3

Max Range: 5.8408. Min Range: -5.8408

Max Act: 5.4970. Min Act: -0.1700

Data Index: 855937 (C4 (Web Text))

Max Activating Token Index: 374

Text #4

Max Range: 5.8408. Min Range: -5.8408

Max Act: 5.4658. Min Act: -0.1700

Data Index: 1094334 (C4 (Web Text))

Max Activating Token Index: 514

Text #5

Max Range: 5.8408. Min Range: -5.8408

Max Act: 5.4345. Min Act: -0.1700

Data Index: 1184670 (C4 (Web Text))

Max Activating Token Index: 363

Text #6

Max Range: 5.8408. Min Range: -5.8408

Max Act: 5.4658. Min Act: -0.1700

Data Index: 156251 (C4 (Web Text))

Max Activating Token Index: 249

Text #7

Max Range: 5.8408. Min Range: -5.8408

Max Act: 5.4658. Min Act: -0.1700

Data Index: 81853 (C4 (Web Text))

Max Activating Token Index: 795

Text #8

Max Range: 5.8408. Min Range: -5.8408

Max Act: 5.4345. Min Act: -0.1700

Data Index: 477618 (C4 (Web Text))

Max Activating Token Index: 874

Text #9

Max Range: 5.8408. Min Range: -5.8408

Max Act: 5.4033. Min Act: -0.1700

Data Index: 365243 (C4 (Web Text))

Max Activating Token Index: 330

Text #10

Max Range: 5.8408. Min Range: -5.8408

Max Act: 5.3408. Min Act: -0.1700

Data Index: 421240 (C4 (Web Text))

Max Activating Token Index: 820

Text #11

Max Range: 5.8408. Min Range: -5.8408

Max Act: 5.3720. Min Act: -0.1700

Data Index: 1177003 (C4 (Web Text))

Max Activating Token Index: 822

Text #12

Max Range: 5.8408. Min Range: -5.8408

Max Act: 5.2783. Min Act: -0.1700

Data Index: 706595 (C4 (Web Text))

Max Activating Token Index: 733

Text #13

Max Range: 5.8408. Min Range: -5.8408

Max Act: 5.2470. Min Act: -0.1700

Data Index: 1174850 (C4 (Web Text))

Max Activating Token Index: 456

Text #14

Max Range: 5.8408. Min Range: -5.8408

Max Act: 5.2783. Min Act: -0.1700

Data Index: 314402 (C4 (Web Text))

Max Activating Token Index: 671

Text #15

Max Range: 5.8408. Min Range: -5.8408

Max Act: 5.2470. Min Act: -0.1700

Data Index: 1053725 (C4 (Web Text))

Max Activating Token Index: 633

Text #16

Max Range: 5.8408. Min Range: -5.8408

Max Act: 5.2783. Min Act: -0.1700

Data Index: 1113456 (C4 (Web Text))

Max Activating Token Index: 400

Text #17

Max Range: 5.8408. Min Range: -5.8408

Max Act: 5.2470. Min Act: -0.1700

Data Index: 716129 (C4 (Web Text))

Max Activating Token Index: 856

Text #18

Max Range: 5.8408. Min Range: -5.8408

Max Act: 5.1845. Min Act: -0.1700

Data Index: 834668 (C4 (Web Text))

Max Activating Token Index: 86

Text #19

Max Range: 5.8408. Min Range: -5.8408

Max Act: 5.1220. Min Act: -0.1700

Data Index: 85851 (C4 (Web Text))

Max Activating Token Index: 960