Model: GELU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 1399 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')

Text #0

Max Range: 3.1138. Min Range: -3.1138

Max Act: 3.1138. Min Act: -0.1700

Data Index: 1641688 (Python Code)

Max Activating Token Index: 615

Text #1

Max Range: 3.1138. Min Range: -3.1138

Max Act: 2.7013. Min Act: -0.1700

Data Index: 402188 (C4 (Web Text))

Max Activating Token Index: 446

Text #2

Max Range: 3.1138. Min Range: -3.1138

Max Act: 2.6692. Min Act: -0.1700

Data Index: 241499 (C4 (Web Text))

Max Activating Token Index: 108

Text #3

Max Range: 3.1138. Min Range: -3.1138

Max Act: 2.7013. Min Act: -0.1700

Data Index: 1199978 (C4 (Web Text))

Max Activating Token Index: 589

Text #4

Max Range: 3.1138. Min Range: -3.1138

Max Act: 2.6532. Min Act: -0.1700

Data Index: 384311 (C4 (Web Text))

Max Activating Token Index: 824

Text #5

Max Range: 3.1138. Min Range: -3.1138

Max Act: 2.6211. Min Act: -0.1700

Data Index: 223735 (C4 (Web Text))

Max Activating Token Index: 657

Text #6

Max Range: 3.1138. Min Range: -3.1138

Max Act: 2.6050. Min Act: -0.1700

Data Index: 729170 (C4 (Web Text))

Max Activating Token Index: 218

Text #7

Max Range: 3.1138. Min Range: -3.1138

Max Act: 2.6211. Min Act: -0.1700

Data Index: 4664 (C4 (Web Text))

Max Activating Token Index: 517

Text #8

Max Range: 3.1138. Min Range: -3.1138

Max Act: 2.6050. Min Act: -0.1700

Data Index: 1268836 (C4 (Web Text))

Max Activating Token Index: 867

Text #9

Max Range: 3.1138. Min Range: -3.1138

Max Act: 2.5889. Min Act: -0.1700

Data Index: 585836 (C4 (Web Text))

Max Activating Token Index: 840

Text #10

Max Range: 3.1138. Min Range: -3.1138

Max Act: 2.5889. Min Act: -0.1700

Data Index: 392108 (C4 (Web Text))

Max Activating Token Index: 804

Text #11

Max Range: 3.1138. Min Range: -3.1138

Max Act: 2.5889. Min Act: -0.1700

Data Index: 1185001 (C4 (Web Text))

Max Activating Token Index: 928

Text #12

Max Range: 3.1138. Min Range: -3.1138

Max Act: 2.6050. Min Act: -0.1700

Data Index: 1170305 (C4 (Web Text))

Max Activating Token Index: 528

Text #13

Max Range: 3.1138. Min Range: -3.1138

Max Act: 2.5728. Min Act: -0.1700

Data Index: 717778 (C4 (Web Text))

Max Activating Token Index: 861

Text #14

Max Range: 3.1138. Min Range: -3.1138

Max Act: 2.5889. Min Act: -0.1700

Data Index: 1158216 (C4 (Web Text))

Max Activating Token Index: 746

Text #15

Max Range: 3.1138. Min Range: -3.1138

Max Act: 2.5405. Min Act: -0.1700

Data Index: 630126 (C4 (Web Text))

Max Activating Token Index: 88

Text #16

Max Range: 3.1138. Min Range: -3.1138

Max Act: 2.5567. Min Act: -0.1700

Data Index: 662786 (C4 (Web Text))

Max Activating Token Index: 395

Text #17

Max Range: 3.1138. Min Range: -3.1138

Max Act: 2.5567. Min Act: -0.1700

Data Index: 1010618 (C4 (Web Text))

Max Activating Token Index: 853

Text #18

Max Range: 3.1138. Min Range: -3.1138

Max Act: 2.5567. Min Act: -0.1700

Data Index: 24126 (C4 (Web Text))

Max Activating Token Index: 811

Text #19

Max Range: 3.1138. Min Range: -3.1138

Max Act: 2.5405. Min Act: -0.1700

Data Index: 762387 (C4 (Web Text))

Max Activating Token Index: 648