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

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

Neuron 1142 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.9735. Min Range: -3.9735

Max Act: 3.9735. Min Act: -0.1700

Data Index: 1295257 (C4 (Web Text))

Max Activating Token Index: 932

Text #1

Max Range: 3.9735. Min Range: -3.9735

Max Act: 3.9735. Min Act: -0.1700

Data Index: 863084 (C4 (Web Text))

Max Activating Token Index: 402

Text #2

Max Range: 3.9735. Min Range: -3.9735

Max Act: 3.9266. Min Act: -0.1700

Data Index: 773203 (C4 (Web Text))

Max Activating Token Index: 170

Text #3

Max Range: 3.9735. Min Range: -3.9735

Max Act: 3.9110. Min Act: -0.1700

Data Index: 354176 (C4 (Web Text))

Max Activating Token Index: 96

Text #4

Max Range: 3.9735. Min Range: -3.9735

Max Act: 3.9110. Min Act: -0.1700

Data Index: 1139355 (C4 (Web Text))

Max Activating Token Index: 425

Text #5

Max Range: 3.9735. Min Range: -3.9735

Max Act: 3.8484. Min Act: -0.1700

Data Index: 311077 (C4 (Web Text))

Max Activating Token Index: 35

Text #6

Max Range: 3.9735. Min Range: -3.9735

Max Act: 3.8328. Min Act: -0.1700

Data Index: 1469198 (Python Code)

Max Activating Token Index: 617

Text #7

Max Range: 3.9735. Min Range: -3.9735

Max Act: 3.8015. Min Act: -0.1700

Data Index: 320355 (C4 (Web Text))

Max Activating Token Index: 74

Text #8

Max Range: 3.9735. Min Range: -3.9735

Max Act: 3.8172. Min Act: -0.1700

Data Index: 1079665 (C4 (Web Text))

Max Activating Token Index: 49

Text #9

Max Range: 3.9735. Min Range: -3.9735

Max Act: 3.8172. Min Act: -0.1700

Data Index: 336887 (C4 (Web Text))

Max Activating Token Index: 678

Text #10

Max Range: 3.9735. Min Range: -3.9735

Max Act: 3.8015. Min Act: -0.1700

Data Index: 152462 (C4 (Web Text))

Max Activating Token Index: 585

Text #11

Max Range: 3.9735. Min Range: -3.9735

Max Act: 3.7859. Min Act: -0.1700

Data Index: 810685 (C4 (Web Text))

Max Activating Token Index: 559

Text #12

Max Range: 3.9735. Min Range: -3.9735

Max Act: 3.7389. Min Act: -0.1700

Data Index: 861367 (C4 (Web Text))

Max Activating Token Index: 5

Text #13

Max Range: 3.9735. Min Range: -3.9735

Max Act: 3.7859. Min Act: -0.1700

Data Index: 76394 (C4 (Web Text))

Max Activating Token Index: 463

Text #14

Max Range: 3.9735. Min Range: -3.9735

Max Act: 3.7546. Min Act: -0.1700

Data Index: 90558 (C4 (Web Text))

Max Activating Token Index: 51

Text #15

Max Range: 3.9735. Min Range: -3.9735

Max Act: 3.7546. Min Act: -0.1700

Data Index: 66936 (C4 (Web Text))

Max Activating Token Index: 46

Text #16

Max Range: 3.9735. Min Range: -3.9735

Max Act: 3.7546. Min Act: -0.1700

Data Index: 362139 (C4 (Web Text))

Max Activating Token Index: 885

Text #17

Max Range: 3.9735. Min Range: -3.9735

Max Act: 3.7389. Min Act: -0.1700

Data Index: 1292559 (C4 (Web Text))

Max Activating Token Index: 330

Text #18

Max Range: 3.9735. Min Range: -3.9735

Max Act: 3.7389. Min Act: -0.1700

Data Index: 765397 (C4 (Web Text))

Max Activating Token Index: 394

Text #19

Max Range: 3.9735. Min Range: -3.9735

Max Act: 3.7389. Min Act: -0.1700

Data Index: 880236 (C4 (Web Text))

Max Activating Token Index: 177