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

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

Neuron 1360 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.6575. Min Range: -3.6575

Max Act: 3.6575. Min Act: -0.1700

Data Index: 1505884 (Python Code)

Max Activating Token Index: 892

Text #1

Max Range: 3.6575. Min Range: -3.6575

Max Act: 3.6106. Min Act: -0.1700

Data Index: 1516872 (Python Code)

Max Activating Token Index: 119

Text #2

Max Range: 3.6575. Min Range: -3.6575

Max Act: 3.5166. Min Act: -0.1700

Data Index: 12804 (C4 (Web Text))

Max Activating Token Index: 217

Text #3

Max Range: 3.6575. Min Range: -3.6575

Max Act: 3.4853. Min Act: -0.1700

Data Index: 326683 (C4 (Web Text))

Max Activating Token Index: 917

Text #4

Max Range: 3.6575. Min Range: -3.6575

Max Act: 3.4853. Min Act: -0.1700

Data Index: 300007 (C4 (Web Text))

Max Activating Token Index: 963

Text #5

Max Range: 3.6575. Min Range: -3.6575

Max Act: 3.4853. Min Act: -0.1700

Data Index: 1298124 (C4 (Web Text))

Max Activating Token Index: 413

Text #6

Max Range: 3.6575. Min Range: -3.6575

Max Act: 3.4382. Min Act: -0.1700

Data Index: 1167459 (C4 (Web Text))

Max Activating Token Index: 163

Text #7

Max Range: 3.6575. Min Range: -3.6575

Max Act: 3.4539. Min Act: -0.1700

Data Index: 1059536 (C4 (Web Text))

Max Activating Token Index: 515

Text #8

Max Range: 3.6575. Min Range: -3.6575

Max Act: 3.4069. Min Act: -0.1700

Data Index: 824522 (C4 (Web Text))

Max Activating Token Index: 456

Text #9

Max Range: 3.6575. Min Range: -3.6575

Max Act: 3.4069. Min Act: -0.1700

Data Index: 547158 (C4 (Web Text))

Max Activating Token Index: 651

Text #10

Max Range: 3.6575. Min Range: -3.6575

Max Act: 3.3912. Min Act: -0.1700

Data Index: 1179261 (C4 (Web Text))

Max Activating Token Index: 638

Text #11

Max Range: 3.6575. Min Range: -3.6575

Max Act: 3.4069. Min Act: -0.1700

Data Index: 204885 (C4 (Web Text))

Max Activating Token Index: 22

Text #12

Max Range: 3.6575. Min Range: -3.6575

Max Act: 3.3755. Min Act: -0.1700

Data Index: 1362227 (Python Code)

Max Activating Token Index: 667

Text #13

Max Range: 3.6575. Min Range: -3.6575

Max Act: 3.3755. Min Act: -0.1700

Data Index: 844790 (C4 (Web Text))

Max Activating Token Index: 1000

Text #14

Max Range: 3.6575. Min Range: -3.6575

Max Act: 3.3755. Min Act: -0.1700

Data Index: 122348 (C4 (Web Text))

Max Activating Token Index: 426

Text #15

Max Range: 3.6575. Min Range: -3.6575

Max Act: 3.3598. Min Act: -0.1700

Data Index: 206140 (C4 (Web Text))

Max Activating Token Index: 455

Text #16

Max Range: 3.6575. Min Range: -3.6575

Max Act: 3.3598. Min Act: -0.1700

Data Index: 863311 (C4 (Web Text))

Max Activating Token Index: 723

Text #17

Max Range: 3.6575. Min Range: -3.6575

Max Act: 3.3598. Min Act: -0.1700

Data Index: 1276516 (C4 (Web Text))

Max Activating Token Index: 352

Text #18

Max Range: 3.6575. Min Range: -3.6575

Max Act: 3.3598. Min Act: -0.1700

Data Index: 731719 (C4 (Web Text))

Max Activating Token Index: 562

Text #19

Max Range: 3.6575. Min Range: -3.6575

Max Act: 3.3441. Min Act: -0.1700

Data Index: 1021238 (C4 (Web Text))

Max Activating Token Index: 670