Model: GELU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 1331 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-3l')

Text #0

Max Range: 3.8694. Min Range: -3.8694

Max Act: 3.8694. Min Act: -0.1700

Data Index: 1101776 (C4 (Web Text))

Max Activating Token Index: 89

Text #1

Max Range: 3.8694. Min Range: -3.8694

Max Act: 3.8382. Min Act: -0.1700

Data Index: 369045 (C4 (Web Text))

Max Activating Token Index: 415

Text #2

Max Range: 3.8694. Min Range: -3.8694

Max Act: 3.8069. Min Act: -0.1700

Data Index: 489996 (C4 (Web Text))

Max Activating Token Index: 129

Text #3

Max Range: 3.8694. Min Range: -3.8694

Max Act: 3.7443. Min Act: -0.1700

Data Index: 854912 (C4 (Web Text))

Max Activating Token Index: 555

Text #4

Max Range: 3.8694. Min Range: -3.8694

Max Act: 3.7443. Min Act: -0.1700

Data Index: 377791 (C4 (Web Text))

Max Activating Token Index: 792

Text #5

Max Range: 3.8694. Min Range: -3.8694

Max Act: 3.6817. Min Act: -0.1700

Data Index: 147706 (C4 (Web Text))

Max Activating Token Index: 278

Text #6

Max Range: 3.8694. Min Range: -3.8694

Max Act: 3.6817. Min Act: -0.1700

Data Index: 739755 (C4 (Web Text))

Max Activating Token Index: 90

Text #7

Max Range: 3.8694. Min Range: -3.8694

Max Act: 3.7130. Min Act: -0.1700

Data Index: 1152907 (C4 (Web Text))

Max Activating Token Index: 288

Text #8

Max Range: 3.8694. Min Range: -3.8694

Max Act: 3.6504. Min Act: -0.1700

Data Index: 1190470 (C4 (Web Text))

Max Activating Token Index: 384

Text #9

Max Range: 3.8694. Min Range: -3.8694

Max Act: 3.6504. Min Act: -0.1700

Data Index: 385159 (C4 (Web Text))

Max Activating Token Index: 689

Text #10

Max Range: 3.8694. Min Range: -3.8694

Max Act: 3.6817. Min Act: -0.1700

Data Index: 77561 (C4 (Web Text))

Max Activating Token Index: 484

Text #11

Max Range: 3.8694. Min Range: -3.8694

Max Act: 3.6817. Min Act: -0.1700

Data Index: 667950 (C4 (Web Text))

Max Activating Token Index: 683

Text #12

Max Range: 3.8694. Min Range: -3.8694

Max Act: 3.6817. Min Act: -0.1700

Data Index: 652271 (C4 (Web Text))

Max Activating Token Index: 399

Text #13

Max Range: 3.8694. Min Range: -3.8694

Max Act: 3.6504. Min Act: -0.1700

Data Index: 748538 (C4 (Web Text))

Max Activating Token Index: 523

Text #14

Max Range: 3.8694. Min Range: -3.8694

Max Act: 3.6191. Min Act: -0.1700

Data Index: 634308 (C4 (Web Text))

Max Activating Token Index: 984

Text #15

Max Range: 3.8694. Min Range: -3.8694

Max Act: 3.6504. Min Act: -0.1700

Data Index: 733412 (C4 (Web Text))

Max Activating Token Index: 851

Text #16

Max Range: 3.8694. Min Range: -3.8694

Max Act: 3.6191. Min Act: -0.1700

Data Index: 1002376 (C4 (Web Text))

Max Activating Token Index: 658

Text #17

Max Range: 3.8694. Min Range: -3.8694

Max Act: 3.6504. Min Act: -0.1700

Data Index: 63025 (C4 (Web Text))

Max Activating Token Index: 355

Text #18

Max Range: 3.8694. Min Range: -3.8694

Max Act: 3.6191. Min Act: -0.1700

Data Index: 558735 (C4 (Web Text))

Max Activating Token Index: 390

Text #19

Max Range: 3.8694. Min Range: -3.8694

Max Act: 3.6817. Min Act: -0.1700

Data Index: 928662 (C4 (Web Text))

Max Activating Token Index: 184