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

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

Neuron 1077 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: 3.4923. Min Range: -3.4923

Max Act: 3.4923. Min Act: -0.1700

Data Index: 710426 (C4 (Web Text))

Max Activating Token Index: 722

Text #1

Max Range: 3.4923. Min Range: -3.4923

Max Act: 3.4453. Min Act: -0.1700

Data Index: 737377 (C4 (Web Text))

Max Activating Token Index: 476

Text #2

Max Range: 3.4923. Min Range: -3.4923

Max Act: 3.4610. Min Act: -0.1700

Data Index: 44115 (C4 (Web Text))

Max Activating Token Index: 446

Text #3

Max Range: 3.4923. Min Range: -3.4923

Max Act: 3.3982. Min Act: -0.1700

Data Index: 1084446 (C4 (Web Text))

Max Activating Token Index: 789

Text #4

Max Range: 3.4923. Min Range: -3.4923

Max Act: 3.3198. Min Act: -0.1700

Data Index: 1012187 (C4 (Web Text))

Max Activating Token Index: 626

Text #5

Max Range: 3.4923. Min Range: -3.4923

Max Act: 3.3198. Min Act: -0.1700

Data Index: 1018293 (C4 (Web Text))

Max Activating Token Index: 268

Text #6

Max Range: 3.4923. Min Range: -3.4923

Max Act: 3.3198. Min Act: -0.1700

Data Index: 922495 (C4 (Web Text))

Max Activating Token Index: 82

Text #7

Max Range: 3.4923. Min Range: -3.4923

Max Act: 3.2726. Min Act: -0.1700

Data Index: 111494 (C4 (Web Text))

Max Activating Token Index: 719

Text #8

Max Range: 3.4923. Min Range: -3.4923

Max Act: 3.2884. Min Act: -0.1700

Data Index: 1078877 (C4 (Web Text))

Max Activating Token Index: 409

Text #9

Max Range: 3.4923. Min Range: -3.4923

Max Act: 3.2569. Min Act: -0.1700

Data Index: 1129101 (C4 (Web Text))

Max Activating Token Index: 628

Text #10

Max Range: 3.4923. Min Range: -3.4923

Max Act: 3.2412. Min Act: -0.1700

Data Index: 1511860 (Python Code)

Max Activating Token Index: 19

Text #11

Max Range: 3.4923. Min Range: -3.4923

Max Act: 3.2412. Min Act: -0.1700

Data Index: 1460801 (Python Code)

Max Activating Token Index: 19

Text #12

Max Range: 3.4923. Min Range: -3.4923

Max Act: 3.2884. Min Act: -0.1700

Data Index: 281905 (C4 (Web Text))

Max Activating Token Index: 438

Text #13

Max Range: 3.4923. Min Range: -3.4923

Max Act: 3.2884. Min Act: -0.1700

Data Index: 1286017 (C4 (Web Text))

Max Activating Token Index: 647

Text #14

Max Range: 3.4923. Min Range: -3.4923

Max Act: 3.2726. Min Act: -0.1700

Data Index: 1055685 (C4 (Web Text))

Max Activating Token Index: 401

Text #15

Max Range: 3.4923. Min Range: -3.4923

Max Act: 3.2726. Min Act: -0.1700

Data Index: 1262366 (C4 (Web Text))

Max Activating Token Index: 361

Text #16

Max Range: 3.4923. Min Range: -3.4923

Max Act: 3.2726. Min Act: -0.1700

Data Index: 869966 (C4 (Web Text))

Max Activating Token Index: 529

Text #17

Max Range: 3.4923. Min Range: -3.4923

Max Act: 3.2884. Min Act: -0.1700

Data Index: 1047112 (C4 (Web Text))

Max Activating Token Index: 649

Text #18

Max Range: 3.4923. Min Range: -3.4923

Max Act: 3.2726. Min Act: -0.1700

Data Index: 942379 (C4 (Web Text))

Max Activating Token Index: 371

Text #19

Max Range: 3.4923. Min Range: -3.4923

Max Act: 3.2098. Min Act: -0.1700

Data Index: 79952 (C4 (Web Text))

Max Activating Token Index: 933