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

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

Neuron 887 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 7.5841. Min Range: -7.5841

Max Act: 7.5841. Min Act: -0.1700

Data Index: 418317 (C4 (Web Text))

Max Activating Token Index: 890

Text #1

Max Range: 7.5841. Min Range: -7.5841

Max Act: 7.3341. Min Act: -0.1700

Data Index: 1008082 (C4 (Web Text))

Max Activating Token Index: 685

Text #2

Max Range: 7.5841. Min Range: -7.5841

Max Act: 7.3029. Min Act: -0.1700

Data Index: 1300427 (C4 (Web Text))

Max Activating Token Index: 496

Text #3

Max Range: 7.5841. Min Range: -7.5841

Max Act: 7.2404. Min Act: -0.1700

Data Index: 1223531 (C4 (Web Text))

Max Activating Token Index: 576

Text #4

Max Range: 7.5841. Min Range: -7.5841

Max Act: 7.2404. Min Act: -0.1700

Data Index: 1202682 (C4 (Web Text))

Max Activating Token Index: 370

Text #5

Max Range: 7.5841. Min Range: -7.5841

Max Act: 7.1466. Min Act: -0.1700

Data Index: 788951 (C4 (Web Text))

Max Activating Token Index: 734

Text #6

Max Range: 7.5841. Min Range: -7.5841

Max Act: 7.1154. Min Act: -0.1700

Data Index: 1217909 (C4 (Web Text))

Max Activating Token Index: 215

Text #7

Max Range: 7.5841. Min Range: -7.5841

Max Act: 7.1154. Min Act: -0.1700

Data Index: 677342 (C4 (Web Text))

Max Activating Token Index: 468

Text #8

Max Range: 7.5841. Min Range: -7.5841

Max Act: 7.0529. Min Act: -0.1700

Data Index: 1031050 (C4 (Web Text))

Max Activating Token Index: 647

Text #9

Max Range: 7.5841. Min Range: -7.5841

Max Act: 7.0841. Min Act: -0.1700

Data Index: 1142629 (C4 (Web Text))

Max Activating Token Index: 124

Text #10

Max Range: 7.5841. Min Range: -7.5841

Max Act: 7.0529. Min Act: -0.1698

Data Index: 314427 (C4 (Web Text))

Max Activating Token Index: 303

Text #11

Max Range: 7.5841. Min Range: -7.5841

Max Act: 7.0529. Min Act: -0.1700

Data Index: 1165883 (C4 (Web Text))

Max Activating Token Index: 411

Text #12

Max Range: 7.5841. Min Range: -7.5841

Max Act: 7.0529. Min Act: -0.1700

Data Index: 740783 (C4 (Web Text))

Max Activating Token Index: 295

Text #13

Max Range: 7.5841. Min Range: -7.5841

Max Act: 7.0216. Min Act: -0.1700

Data Index: 534764 (C4 (Web Text))

Max Activating Token Index: 807

Text #14

Max Range: 7.5841. Min Range: -7.5841

Max Act: 6.9591. Min Act: -0.1700

Data Index: 1209538 (C4 (Web Text))

Max Activating Token Index: 434

Text #15

Max Range: 7.5841. Min Range: -7.5841

Max Act: 6.9279. Min Act: -0.1700

Data Index: 709814 (C4 (Web Text))

Max Activating Token Index: 195

Text #16

Max Range: 7.5841. Min Range: -7.5841

Max Act: 6.8966. Min Act: -0.1700

Data Index: 31158 (C4 (Web Text))

Max Activating Token Index: 625

Text #17

Max Range: 7.5841. Min Range: -7.5841

Max Act: 6.8654. Min Act: -0.1700

Data Index: 871235 (C4 (Web Text))

Max Activating Token Index: 230

Text #18

Max Range: 7.5841. Min Range: -7.5841

Max Act: 6.8654. Min Act: -0.1700

Data Index: 663159 (C4 (Web Text))

Max Activating Token Index: 473

Text #19

Max Range: 7.5841. Min Range: -7.5841

Max Act: 6.8341. Min Act: -0.1700

Data Index: 983409 (C4 (Web Text))

Max Activating Token Index: 835