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

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

Neuron 330 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: 5.3769. Min Range: -5.3769

Max Act: 5.3769. Min Act: -0.1700

Data Index: 784372 (C4 (Web Text))

Max Activating Token Index: 582

Text #1

Max Range: 5.3769. Min Range: -5.3769

Max Act: 5.2519. Min Act: -0.1700

Data Index: 256498 (C4 (Web Text))

Max Activating Token Index: 322

Text #2

Max Range: 5.3769. Min Range: -5.3769

Max Act: 5.2519. Min Act: -0.1700

Data Index: 394849 (C4 (Web Text))

Max Activating Token Index: 380

Text #3

Max Range: 5.3769. Min Range: -5.3769

Max Act: 5.2832. Min Act: -0.1700

Data Index: 174325 (C4 (Web Text))

Max Activating Token Index: 805

Text #4

Max Range: 5.3769. Min Range: -5.3769

Max Act: 5.3457. Min Act: -0.1700

Data Index: 806787 (C4 (Web Text))

Max Activating Token Index: 608

Text #5

Max Range: 5.3769. Min Range: -5.3769

Max Act: 5.2207. Min Act: -0.1700

Data Index: 827630 (C4 (Web Text))

Max Activating Token Index: 351

Text #6

Max Range: 5.3769. Min Range: -5.3769

Max Act: 5.3457. Min Act: -0.1700

Data Index: 716957 (C4 (Web Text))

Max Activating Token Index: 392

Text #7

Max Range: 5.3769. Min Range: -5.3769

Max Act: 5.2832. Min Act: -0.1700

Data Index: 886938 (C4 (Web Text))

Max Activating Token Index: 548

Text #8

Max Range: 5.3769. Min Range: -5.3769

Max Act: 5.2832. Min Act: -0.1700

Data Index: 648560 (C4 (Web Text))

Max Activating Token Index: 599

Text #9

Max Range: 5.3769. Min Range: -5.3769

Max Act: 5.1894. Min Act: -0.1700

Data Index: 1220974 (C4 (Web Text))

Max Activating Token Index: 123

Text #10

Max Range: 5.3769. Min Range: -5.3769

Max Act: 5.3144. Min Act: -0.1700

Data Index: 624638 (C4 (Web Text))

Max Activating Token Index: 468

Text #11

Max Range: 5.3769. Min Range: -5.3769

Max Act: 5.1894. Min Act: -0.1700

Data Index: 304475 (C4 (Web Text))

Max Activating Token Index: 512

Text #12

Max Range: 5.3769. Min Range: -5.3769

Max Act: 5.1894. Min Act: -0.1700

Data Index: 956661 (C4 (Web Text))

Max Activating Token Index: 507

Text #13

Max Range: 5.3769. Min Range: -5.3769

Max Act: 5.2519. Min Act: -0.1700

Data Index: 1020593 (C4 (Web Text))

Max Activating Token Index: 603

Text #14

Max Range: 5.3769. Min Range: -5.3769

Max Act: 5.2207. Min Act: -0.1700

Data Index: 1078897 (C4 (Web Text))

Max Activating Token Index: 970

Text #15

Max Range: 5.3769. Min Range: -5.3769

Max Act: 5.1894. Min Act: -0.1700

Data Index: 12522 (C4 (Web Text))

Max Activating Token Index: 553

Text #16

Max Range: 5.3769. Min Range: -5.3769

Max Act: 5.1269. Min Act: -0.1700

Data Index: 635382 (C4 (Web Text))

Max Activating Token Index: 382

Text #17

Max Range: 5.3769. Min Range: -5.3769

Max Act: 5.1894. Min Act: -0.1700

Data Index: 578981 (C4 (Web Text))

Max Activating Token Index: 412

Text #18

Max Range: 5.3769. Min Range: -5.3769

Max Act: 5.1894. Min Act: -0.1700

Data Index: 199677 (C4 (Web Text))

Max Activating Token Index: 380

Text #19

Max Range: 5.3769. Min Range: -5.3769

Max Act: 5.1894. Min Act: -0.1700

Data Index: 949297 (C4 (Web Text))

Max Activating Token Index: 449