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

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

Neuron 268 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: 8.0390. Min Range: -8.0390

Max Act: 8.0390. Min Act: -0.1700

Data Index: 996363 (C4 (Web Text))

Max Activating Token Index: 616

Text #1

Max Range: 8.0390. Min Range: -8.0390

Max Act: 7.7890. Min Act: -0.1700

Data Index: 389966 (C4 (Web Text))

Max Activating Token Index: 283

Text #2

Max Range: 8.0390. Min Range: -8.0390

Max Act: 7.7890. Min Act: -0.1700

Data Index: 346361 (C4 (Web Text))

Max Activating Token Index: 957

Text #3

Max Range: 8.0390. Min Range: -8.0390

Max Act: 7.9140. Min Act: -0.1700

Data Index: 1101954 (C4 (Web Text))

Max Activating Token Index: 745

Text #4

Max Range: 8.0390. Min Range: -8.0390

Max Act: 7.6640. Min Act: -0.1700

Data Index: 268518 (C4 (Web Text))

Max Activating Token Index: 461

Text #5

Max Range: 8.0390. Min Range: -8.0390

Max Act: 7.6953. Min Act: -0.1700

Data Index: 1159565 (C4 (Web Text))

Max Activating Token Index: 473

Text #6

Max Range: 8.0390. Min Range: -8.0390

Max Act: 7.6328. Min Act: -0.1700

Data Index: 835017 (C4 (Web Text))

Max Activating Token Index: 875

Text #7

Max Range: 8.0390. Min Range: -8.0390

Max Act: 7.6640. Min Act: -0.1700

Data Index: 232705 (C4 (Web Text))

Max Activating Token Index: 359

Text #8

Max Range: 8.0390. Min Range: -8.0390

Max Act: 7.5703. Min Act: -0.1700

Data Index: 149851 (C4 (Web Text))

Max Activating Token Index: 493

Text #9

Max Range: 8.0390. Min Range: -8.0390

Max Act: 7.6328. Min Act: -0.1700

Data Index: 1147405 (C4 (Web Text))

Max Activating Token Index: 608

Text #10

Max Range: 8.0390. Min Range: -8.0390

Max Act: 7.5703. Min Act: -0.1700

Data Index: 958464 (C4 (Web Text))

Max Activating Token Index: 346

Text #11

Max Range: 8.0390. Min Range: -8.0390

Max Act: 7.4765. Min Act: -0.1700

Data Index: 842152 (C4 (Web Text))

Max Activating Token Index: 569

Text #12

Max Range: 8.0390. Min Range: -8.0390

Max Act: 7.5390. Min Act: -0.1700

Data Index: 1328157 (C4 (Web Text))

Max Activating Token Index: 651

Text #13

Max Range: 8.0390. Min Range: -8.0390

Max Act: 7.3515. Min Act: -0.1700

Data Index: 1332535 (C4 (Web Text))

Max Activating Token Index: 115

Text #14

Max Range: 8.0390. Min Range: -8.0390

Max Act: 7.4140. Min Act: -0.1700

Data Index: 1208092 (C4 (Web Text))

Max Activating Token Index: 228

Text #15

Max Range: 8.0390. Min Range: -8.0390

Max Act: 7.3828. Min Act: -0.1700

Data Index: 467365 (C4 (Web Text))

Max Activating Token Index: 711

Text #16

Max Range: 8.0390. Min Range: -8.0390

Max Act: 7.3515. Min Act: -0.1700

Data Index: 856980 (C4 (Web Text))

Max Activating Token Index: 411

Text #17

Max Range: 8.0390. Min Range: -8.0390

Max Act: 7.5078. Min Act: -0.1700

Data Index: 905803 (C4 (Web Text))

Max Activating Token Index: 656

Text #18

Max Range: 8.0390. Min Range: -8.0390

Max Act: 7.3515. Min Act: -0.1700

Data Index: 1007157 (C4 (Web Text))

Max Activating Token Index: 714

Text #19

Max Range: 8.0390. Min Range: -8.0390

Max Act: 7.3203. Min Act: -0.1700

Data Index: 583817 (C4 (Web Text))

Max Activating Token Index: 367