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

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

Neuron 1751 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.3331. Min Range: -3.3331

Max Act: 3.3331. Min Act: -0.1700

Data Index: 383348 (C4 (Web Text))

Max Activating Token Index: 599

Text #1

Max Range: 3.3331. Min Range: -3.3331

Max Act: 3.2546. Min Act: -0.1700

Data Index: 904746 (C4 (Web Text))

Max Activating Token Index: 128

Text #2

Max Range: 3.3331. Min Range: -3.3331

Max Act: 3.1760. Min Act: -0.1700

Data Index: 1094741 (C4 (Web Text))

Max Activating Token Index: 423

Text #3

Max Range: 3.3331. Min Range: -3.3331

Max Act: 3.1917. Min Act: -0.1700

Data Index: 49228 (C4 (Web Text))

Max Activating Token Index: 997

Text #4

Max Range: 3.3331. Min Range: -3.3331

Max Act: 3.1917. Min Act: -0.1700

Data Index: 241481 (C4 (Web Text))

Max Activating Token Index: 856

Text #5

Max Range: 3.3331. Min Range: -3.3331

Max Act: 3.1917. Min Act: -0.1700

Data Index: 436030 (C4 (Web Text))

Max Activating Token Index: 189

Text #6

Max Range: 3.3331. Min Range: -3.3331

Max Act: 3.1760. Min Act: -0.1700

Data Index: 631141 (C4 (Web Text))

Max Activating Token Index: 305

Text #7

Max Range: 3.3331. Min Range: -3.3331

Max Act: 3.1445. Min Act: -0.1700

Data Index: 296147 (C4 (Web Text))

Max Activating Token Index: 253

Text #8

Max Range: 3.3331. Min Range: -3.3331

Max Act: 3.1602. Min Act: -0.1700

Data Index: 619931 (C4 (Web Text))

Max Activating Token Index: 826

Text #9

Max Range: 3.3331. Min Range: -3.3331

Max Act: 3.1445. Min Act: -0.1700

Data Index: 1066926 (C4 (Web Text))

Max Activating Token Index: 316

Text #10

Max Range: 3.3331. Min Range: -3.3331

Max Act: 3.1287. Min Act: -0.1700

Data Index: 527654 (C4 (Web Text))

Max Activating Token Index: 269

Text #11

Max Range: 3.3331. Min Range: -3.3331

Max Act: 3.1445. Min Act: -0.1700

Data Index: 1331632 (C4 (Web Text))

Max Activating Token Index: 135

Text #12

Max Range: 3.3331. Min Range: -3.3331

Max Act: 3.1445. Min Act: -0.1700

Data Index: 1060804 (C4 (Web Text))

Max Activating Token Index: 897

Text #13

Max Range: 3.3331. Min Range: -3.3331

Max Act: 3.1445. Min Act: -0.1700

Data Index: 1060469 (C4 (Web Text))

Max Activating Token Index: 155

Text #14

Max Range: 3.3331. Min Range: -3.3331

Max Act: 3.1445. Min Act: -0.1700

Data Index: 1208743 (C4 (Web Text))

Max Activating Token Index: 841

Text #15

Max Range: 3.3331. Min Range: -3.3331

Max Act: 3.1287. Min Act: -0.1700

Data Index: 812626 (C4 (Web Text))

Max Activating Token Index: 36

Text #16

Max Range: 3.3331. Min Range: -3.3331

Max Act: 3.1287. Min Act: -0.1700

Data Index: 271064 (C4 (Web Text))

Max Activating Token Index: 320

Text #17

Max Range: 3.3331. Min Range: -3.3331

Max Act: 3.1445. Min Act: -0.1700

Data Index: 1059068 (C4 (Web Text))

Max Activating Token Index: 952

Text #18

Max Range: 3.3331. Min Range: -3.3331

Max Act: 3.1287. Min Act: -0.1700

Data Index: 93742 (C4 (Web Text))

Max Activating Token Index: 368

Text #19

Max Range: 3.3331. Min Range: -3.3331

Max Act: 3.1130. Min Act: -0.1700

Data Index: 1958 (C4 (Web Text))

Max Activating Token Index: 246