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

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

Neuron 1839 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: 3.3301. Min Range: -3.3301

Max Act: 3.3301. Min Act: -0.1700

Data Index: 572182 (C4 (Web Text))

Max Activating Token Index: 580

Text #1

Max Range: 3.3301. Min Range: -3.3301

Max Act: 3.3144. Min Act: -0.1700

Data Index: 1012932 (C4 (Web Text))

Max Activating Token Index: 488

Text #2

Max Range: 3.3301. Min Range: -3.3301

Max Act: 3.2359. Min Act: -0.1700

Data Index: 982303 (C4 (Web Text))

Max Activating Token Index: 823

Text #3

Max Range: 3.3301. Min Range: -3.3301

Max Act: 3.2201. Min Act: -0.1700

Data Index: 1143994 (C4 (Web Text))

Max Activating Token Index: 452

Text #4

Max Range: 3.3301. Min Range: -3.3301

Max Act: 3.2044. Min Act: -0.1700

Data Index: 421861 (C4 (Web Text))

Max Activating Token Index: 834

Text #5

Max Range: 3.3301. Min Range: -3.3301

Max Act: 3.2044. Min Act: -0.1700

Data Index: 492578 (C4 (Web Text))

Max Activating Token Index: 1008

Text #6

Max Range: 3.3301. Min Range: -3.3301

Max Act: 3.1414. Min Act: -0.1700

Data Index: 1355514 (C4 (Web Text))

Max Activating Token Index: 252

Text #7

Max Range: 3.3301. Min Range: -3.3301

Max Act: 3.1729. Min Act: -0.1700

Data Index: 164601 (C4 (Web Text))

Max Activating Token Index: 574

Text #8

Max Range: 3.3301. Min Range: -3.3301

Max Act: 3.1257. Min Act: -0.1700

Data Index: 403734 (C4 (Web Text))

Max Activating Token Index: 549

Text #9

Max Range: 3.3301. Min Range: -3.3301

Max Act: 3.1257. Min Act: -0.1700

Data Index: 851940 (C4 (Web Text))

Max Activating Token Index: 435

Text #10

Max Range: 3.3301. Min Range: -3.3301

Max Act: 3.1257. Min Act: -0.1700

Data Index: 284937 (C4 (Web Text))

Max Activating Token Index: 569

Text #11

Max Range: 3.3301. Min Range: -3.3301

Max Act: 3.1414. Min Act: -0.1700

Data Index: 1192595 (C4 (Web Text))

Max Activating Token Index: 649

Text #12

Max Range: 3.3301. Min Range: -3.3301

Max Act: 3.1257. Min Act: -0.1700

Data Index: 673016 (C4 (Web Text))

Max Activating Token Index: 417

Text #13

Max Range: 3.3301. Min Range: -3.3301

Max Act: 3.0784. Min Act: -0.1700

Data Index: 1069715 (C4 (Web Text))

Max Activating Token Index: 948

Text #14

Max Range: 3.3301. Min Range: -3.3301

Max Act: 3.0942. Min Act: -0.1700

Data Index: 828105 (C4 (Web Text))

Max Activating Token Index: 214

Text #15

Max Range: 3.3301. Min Range: -3.3301

Max Act: 3.0784. Min Act: -0.1700

Data Index: 632157 (C4 (Web Text))

Max Activating Token Index: 689

Text #16

Max Range: 3.3301. Min Range: -3.3301

Max Act: 3.0626. Min Act: -0.1700

Data Index: 496199 (C4 (Web Text))

Max Activating Token Index: 863

Text #17

Max Range: 3.3301. Min Range: -3.3301

Max Act: 3.0468. Min Act: -0.1700

Data Index: 1491940 (Python Code)

Max Activating Token Index: 867

Text #18

Max Range: 3.3301. Min Range: -3.3301

Max Act: 3.0468. Min Act: -0.1700

Data Index: 853454 (C4 (Web Text))

Max Activating Token Index: 656

Text #19

Max Range: 3.3301. Min Range: -3.3301

Max Act: 3.0310. Min Act: -0.1700

Data Index: 684347 (C4 (Web Text))

Max Activating Token Index: 638