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

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

Neuron 1389 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: 3.7220. Min Range: -3.7220

Max Act: 3.7220. Min Act: -0.1700

Data Index: 536905 (C4 (Web Text))

Max Activating Token Index: 609

Text #1

Max Range: 3.7220. Min Range: -3.7220

Max Act: 3.6907. Min Act: -0.1700

Data Index: 313161 (C4 (Web Text))

Max Activating Token Index: 316

Text #2

Max Range: 3.7220. Min Range: -3.7220

Max Act: 3.6594. Min Act: -0.1700

Data Index: 1164273 (C4 (Web Text))

Max Activating Token Index: 42

Text #3

Max Range: 3.7220. Min Range: -3.7220

Max Act: 3.5968. Min Act: -0.1700

Data Index: 838564 (C4 (Web Text))

Max Activating Token Index: 857

Text #4

Max Range: 3.7220. Min Range: -3.7220

Max Act: 3.5498. Min Act: -0.1700

Data Index: 34012 (C4 (Web Text))

Max Activating Token Index: 918

Text #5

Max Range: 3.7220. Min Range: -3.7220

Max Act: 3.5655. Min Act: -0.1700

Data Index: 323462 (C4 (Web Text))

Max Activating Token Index: 424

Text #6

Max Range: 3.7220. Min Range: -3.7220

Max Act: 3.5655. Min Act: -0.1700

Data Index: 1346262 (C4 (Web Text))

Max Activating Token Index: 977

Text #7

Max Range: 3.7220. Min Range: -3.7220

Max Act: 3.5342. Min Act: -0.1700

Data Index: 787268 (C4 (Web Text))

Max Activating Token Index: 647

Text #8

Max Range: 3.7220. Min Range: -3.7220

Max Act: 3.5185. Min Act: -0.1700

Data Index: 1256626 (C4 (Web Text))

Max Activating Token Index: 1014

Text #9

Max Range: 3.7220. Min Range: -3.7220

Max Act: 3.5498. Min Act: -0.1700

Data Index: 1262905 (C4 (Web Text))

Max Activating Token Index: 836

Text #10

Max Range: 3.7220. Min Range: -3.7220

Max Act: 3.5185. Min Act: -0.1700

Data Index: 1116294 (C4 (Web Text))

Max Activating Token Index: 319

Text #11

Max Range: 3.7220. Min Range: -3.7220

Max Act: 3.4715. Min Act: -0.1700

Data Index: 187995 (C4 (Web Text))

Max Activating Token Index: 264

Text #12

Max Range: 3.7220. Min Range: -3.7220

Max Act: 3.4872. Min Act: -0.1700

Data Index: 1326875 (C4 (Web Text))

Max Activating Token Index: 350

Text #13

Max Range: 3.7220. Min Range: -3.7220

Max Act: 3.4872. Min Act: -0.1700

Data Index: 591000 (C4 (Web Text))

Max Activating Token Index: 231

Text #14

Max Range: 3.7220. Min Range: -3.7220

Max Act: 3.4402. Min Act: -0.1700

Data Index: 905966 (C4 (Web Text))

Max Activating Token Index: 223

Text #15

Max Range: 3.7220. Min Range: -3.7220

Max Act: 3.4402. Min Act: -0.1700

Data Index: 185233 (C4 (Web Text))

Max Activating Token Index: 103

Text #16

Max Range: 3.7220. Min Range: -3.7220

Max Act: 3.4872. Min Act: -0.1700

Data Index: 874032 (C4 (Web Text))

Max Activating Token Index: 411

Text #17

Max Range: 3.7220. Min Range: -3.7220

Max Act: 3.4402. Min Act: -0.1700

Data Index: 1305776 (C4 (Web Text))

Max Activating Token Index: 925

Text #18

Max Range: 3.7220. Min Range: -3.7220

Max Act: 3.4402. Min Act: -0.1700

Data Index: 1311793 (C4 (Web Text))

Max Activating Token Index: 182

Text #19

Max Range: 3.7220. Min Range: -3.7220

Max Act: 3.3617. Min Act: -0.1700

Data Index: 833488 (C4 (Web Text))

Max Activating Token Index: 391