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

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

Neuron 1201 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')

Text #0

Max Range: 3.4923. Min Range: -3.4923

Max Act: 3.4923. Min Act: -0.1699

Data Index: 1271514 (C4 (Web Text))

Max Activating Token Index: 533

Text #1

Max Range: 3.4923. Min Range: -3.4923

Max Act: 3.4296. Min Act: -0.1700

Data Index: 82869 (C4 (Web Text))

Max Activating Token Index: 542

Text #2

Max Range: 3.4923. Min Range: -3.4923

Max Act: 3.4610. Min Act: -0.1700

Data Index: 1337307 (C4 (Web Text))

Max Activating Token Index: 695

Text #3

Max Range: 3.4923. Min Range: -3.4923

Max Act: 3.4610. Min Act: -0.1700

Data Index: 685037 (C4 (Web Text))

Max Activating Token Index: 379

Text #4

Max Range: 3.4923. Min Range: -3.4923

Max Act: 3.3198. Min Act: -0.1700

Data Index: 1157659 (C4 (Web Text))

Max Activating Token Index: 773

Text #5

Max Range: 3.4923. Min Range: -3.4923

Max Act: 3.3355. Min Act: -0.1699

Data Index: 711180 (C4 (Web Text))

Max Activating Token Index: 921

Text #6

Max Range: 3.4923. Min Range: -3.4923

Max Act: 3.2884. Min Act: -0.1699

Data Index: 194030 (C4 (Web Text))

Max Activating Token Index: 268

Text #7

Max Range: 3.4923. Min Range: -3.4923

Max Act: 3.2570. Min Act: -0.1629

Data Index: 1584924 (Python Code)

Max Activating Token Index: 956

Text #8

Max Range: 3.4923. Min Range: -3.4923

Max Act: 3.3198. Min Act: -0.1700

Data Index: 1086803 (C4 (Web Text))

Max Activating Token Index: 485

Text #9

Max Range: 3.4923. Min Range: -3.4923

Max Act: 3.3041. Min Act: -0.1700

Data Index: 1115428 (C4 (Web Text))

Max Activating Token Index: 476

Text #10

Max Range: 3.4923. Min Range: -3.4923

Max Act: 3.2727. Min Act: -0.1700

Data Index: 1309782 (C4 (Web Text))

Max Activating Token Index: 579

Text #11

Max Range: 3.4923. Min Range: -3.4923

Max Act: 3.2412. Min Act: -0.1700

Data Index: 676870 (C4 (Web Text))

Max Activating Token Index: 866

Text #12

Max Range: 3.4923. Min Range: -3.4923

Max Act: 3.1783. Min Act: -0.1700

Data Index: 1078825 (C4 (Web Text))

Max Activating Token Index: 508

Text #13

Max Range: 3.4923. Min Range: -3.4923

Max Act: 3.1783. Min Act: -0.1700

Data Index: 882571 (C4 (Web Text))

Max Activating Token Index: 525

Text #14

Max Range: 3.4923. Min Range: -3.4923

Max Act: 3.1783. Min Act: -0.1700

Data Index: 28744 (C4 (Web Text))

Max Activating Token Index: 891

Text #15

Max Range: 3.4923. Min Range: -3.4923

Max Act: 3.1626. Min Act: -0.1699

Data Index: 79100 (C4 (Web Text))

Max Activating Token Index: 318

Text #16

Max Range: 3.4923. Min Range: -3.4923

Max Act: 3.1468. Min Act: -0.1700

Data Index: 1274904 (C4 (Web Text))

Max Activating Token Index: 744

Text #17

Max Range: 3.4923. Min Range: -3.4923

Max Act: 3.1468. Min Act: -0.1700

Data Index: 271074 (C4 (Web Text))

Max Activating Token Index: 428

Text #18

Max Range: 3.4923. Min Range: -3.4923

Max Act: 3.1783. Min Act: -0.1700

Data Index: 1128102 (C4 (Web Text))

Max Activating Token Index: 992

Text #19

Max Range: 3.4923. Min Range: -3.4923

Max Act: 3.1626. Min Act: -0.1700

Data Index: 559456 (C4 (Web Text))

Max Activating Token Index: 929