Model: GELU Model: 2 Layers, 2048 Neurons per Layer

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

Neuron 1868 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-2l')

Text #0

Max Range: 3.9290. Min Range: -3.9290

Max Act: 3.9290. Min Act: -0.1700

Data Index: 998748 (C4 (Web Text))

Max Activating Token Index: 758

Text #1

Max Range: 3.9290. Min Range: -3.9290

Max Act: 3.7413. Min Act: -0.1700

Data Index: 83638 (C4 (Web Text))

Max Activating Token Index: 379

Text #2

Max Range: 3.9290. Min Range: -3.9290

Max Act: 3.7100. Min Act: -0.1700

Data Index: 175692 (C4 (Web Text))

Max Activating Token Index: 313

Text #3

Max Range: 3.9290. Min Range: -3.9290

Max Act: 3.6787. Min Act: -0.1700

Data Index: 21837 (C4 (Web Text))

Max Activating Token Index: 905

Text #4

Max Range: 3.9290. Min Range: -3.9290

Max Act: 3.6787. Min Act: -0.1700

Data Index: 614918 (C4 (Web Text))

Max Activating Token Index: 460

Text #5

Max Range: 3.9290. Min Range: -3.9290

Max Act: 3.6787. Min Act: -0.1700

Data Index: 242967 (C4 (Web Text))

Max Activating Token Index: 370

Text #6

Max Range: 3.9290. Min Range: -3.9290

Max Act: 3.6787. Min Act: -0.1700

Data Index: 323838 (C4 (Web Text))

Max Activating Token Index: 238

Text #7

Max Range: 3.9290. Min Range: -3.9290

Max Act: 3.6787. Min Act: -0.1700

Data Index: 1176429 (C4 (Web Text))

Max Activating Token Index: 682

Text #8

Max Range: 3.9290. Min Range: -3.9290

Max Act: 3.6474. Min Act: -0.1700

Data Index: 353391 (C4 (Web Text))

Max Activating Token Index: 683

Text #9

Max Range: 3.9290. Min Range: -3.9290

Max Act: 3.6161. Min Act: -0.1698

Data Index: 295689 (C4 (Web Text))

Max Activating Token Index: 679

Text #10

Max Range: 3.9290. Min Range: -3.9290

Max Act: 3.6474. Min Act: -0.1700

Data Index: 1008034 (C4 (Web Text))

Max Activating Token Index: 483

Text #11

Max Range: 3.9290. Min Range: -3.9290

Max Act: 3.6474. Min Act: -0.1700

Data Index: 1251417 (C4 (Web Text))

Max Activating Token Index: 510

Text #12

Max Range: 3.9290. Min Range: -3.9290

Max Act: 3.6474. Min Act: -0.1700

Data Index: 1082935 (C4 (Web Text))

Max Activating Token Index: 232

Text #13

Max Range: 3.9290. Min Range: -3.9290

Max Act: 3.6474. Min Act: -0.1700

Data Index: 1191807 (C4 (Web Text))

Max Activating Token Index: 366

Text #14

Max Range: 3.9290. Min Range: -3.9290

Max Act: 3.6161. Min Act: -0.1700

Data Index: 796565 (C4 (Web Text))

Max Activating Token Index: 758

Text #15

Max Range: 3.9290. Min Range: -3.9290

Max Act: 3.6161. Min Act: -0.1700

Data Index: 753573 (C4 (Web Text))

Max Activating Token Index: 692

Text #16

Max Range: 3.9290. Min Range: -3.9290

Max Act: 3.6161. Min Act: -0.1700

Data Index: 733548 (C4 (Web Text))

Max Activating Token Index: 617

Text #17

Max Range: 3.9290. Min Range: -3.9290

Max Act: 3.5848. Min Act: -0.1700

Data Index: 1209819 (C4 (Web Text))

Max Activating Token Index: 107

Text #18

Max Range: 3.9290. Min Range: -3.9290

Max Act: 3.6161. Min Act: -0.1700

Data Index: 70764 (C4 (Web Text))

Max Activating Token Index: 262

Text #19

Max Range: 3.9290. Min Range: -3.9290

Max Act: 3.6161. Min Act: -0.1700

Data Index: 505559 (C4 (Web Text))

Max Activating Token Index: 663