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

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

Neuron 1772 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.1055. Min Range: -5.1055

Max Act: 5.0118. Min Act: -0.1700

Data Index: 998691 (C4 (Web Text))

Max Activating Token Index: 680

Text #1

Max Range: 5.1055. Min Range: -5.1055

Max Act: 5.0743. Min Act: -0.1700

Data Index: 1332091 (C4 (Web Text))

Max Activating Token Index: 683

Text #2

Max Range: 5.1055. Min Range: -5.1055

Max Act: 5.1055. Min Act: -0.1700

Data Index: 553972 (C4 (Web Text))

Max Activating Token Index: 328

Text #3

Max Range: 5.1055. Min Range: -5.1055

Max Act: 4.9805. Min Act: -0.1700

Data Index: 419206 (C4 (Web Text))

Max Activating Token Index: 332

Text #4

Max Range: 5.1055. Min Range: -5.1055

Max Act: 5.0118. Min Act: -0.1700

Data Index: 399266 (C4 (Web Text))

Max Activating Token Index: 53

Text #5

Max Range: 5.1055. Min Range: -5.1055

Max Act: 4.9337. Min Act: -0.1700

Data Index: 709855 (C4 (Web Text))

Max Activating Token Index: 806

Text #6

Max Range: 5.1055. Min Range: -5.1055

Max Act: 4.9493. Min Act: -0.1700

Data Index: 375906 (C4 (Web Text))

Max Activating Token Index: 604

Text #7

Max Range: 5.1055. Min Range: -5.1055

Max Act: 4.9024. Min Act: -0.1700

Data Index: 351324 (C4 (Web Text))

Max Activating Token Index: 658

Text #8

Max Range: 5.1055. Min Range: -5.1055

Max Act: 4.9493. Min Act: -0.1700

Data Index: 371364 (C4 (Web Text))

Max Activating Token Index: 649

Text #9

Max Range: 5.1055. Min Range: -5.1055

Max Act: 4.9024. Min Act: -0.1700

Data Index: 322 (C4 (Web Text))

Max Activating Token Index: 598

Text #10

Max Range: 5.1055. Min Range: -5.1055

Max Act: 4.9180. Min Act: -0.1700

Data Index: 1122660 (C4 (Web Text))

Max Activating Token Index: 301

Text #11

Max Range: 5.1055. Min Range: -5.1055

Max Act: 4.8086. Min Act: -0.1700

Data Index: 1000637 (C4 (Web Text))

Max Activating Token Index: 883

Text #12

Max Range: 5.1055. Min Range: -5.1055

Max Act: 4.8399. Min Act: -0.1700

Data Index: 1412289 (Python Code)

Max Activating Token Index: 872

Text #13

Max Range: 5.1055. Min Range: -5.1055

Max Act: 4.7930. Min Act: -0.1700

Data Index: 422637 (C4 (Web Text))

Max Activating Token Index: 284

Text #14

Max Range: 5.1055. Min Range: -5.1055

Max Act: 4.7930. Min Act: -0.1700

Data Index: 591591 (C4 (Web Text))

Max Activating Token Index: 884

Text #15

Max Range: 5.1055. Min Range: -5.1055

Max Act: 4.7461. Min Act: -0.1700

Data Index: 987825 (C4 (Web Text))

Max Activating Token Index: 895

Text #16

Max Range: 5.1055. Min Range: -5.1055

Max Act: 4.7930. Min Act: -0.1700

Data Index: 529523 (C4 (Web Text))

Max Activating Token Index: 614

Text #17

Max Range: 5.1055. Min Range: -5.1055

Max Act: 4.8086. Min Act: -0.1700

Data Index: 842906 (C4 (Web Text))

Max Activating Token Index: 257

Text #18

Max Range: 5.1055. Min Range: -5.1055

Max Act: 4.7461. Min Act: -0.1700

Data Index: 754044 (C4 (Web Text))

Max Activating Token Index: 696

Text #19

Max Range: 5.1055. Min Range: -5.1055

Max Act: 4.8086. Min Act: -0.1700

Data Index: 681777 (C4 (Web Text))

Max Activating Token Index: 609