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

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

Neuron 1954 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.1973. Min Range: -4.1973

Max Act: 4.1973. Min Act: -0.1700

Data Index: 604075 (C4 (Web Text))

Max Activating Token Index: 369

Text #1

Max Range: 4.1973. Min Range: -4.1973

Max Act: 4.1035. Min Act: -0.1700

Data Index: 518136 (C4 (Web Text))

Max Activating Token Index: 928

Text #2

Max Range: 4.1973. Min Range: -4.1973

Max Act: 4.0722. Min Act: -0.1700

Data Index: 849019 (C4 (Web Text))

Max Activating Token Index: 101

Text #3

Max Range: 4.1973. Min Range: -4.1973

Max Act: 4.0722. Min Act: -0.1700

Data Index: 68527 (C4 (Web Text))

Max Activating Token Index: 170

Text #4

Max Range: 4.1973. Min Range: -4.1973

Max Act: 4.0722. Min Act: -0.1700

Data Index: 1319004 (C4 (Web Text))

Max Activating Token Index: 397

Text #5

Max Range: 4.1973. Min Range: -4.1973

Max Act: 4.0722. Min Act: -0.1700

Data Index: 1291807 (C4 (Web Text))

Max Activating Token Index: 27

Text #6

Max Range: 4.1973. Min Range: -4.1973

Max Act: 4.0722. Min Act: -0.1700

Data Index: 658463 (C4 (Web Text))

Max Activating Token Index: 643

Text #7

Max Range: 4.1973. Min Range: -4.1973

Max Act: 4.0097. Min Act: -0.1700

Data Index: 913859 (C4 (Web Text))

Max Activating Token Index: 241

Text #8

Max Range: 4.1973. Min Range: -4.1973

Max Act: 3.9472. Min Act: -0.1700

Data Index: 724373 (C4 (Web Text))

Max Activating Token Index: 975

Text #9

Max Range: 4.1973. Min Range: -4.1973

Max Act: 3.9785. Min Act: -0.1700

Data Index: 752093 (C4 (Web Text))

Max Activating Token Index: 46

Text #10

Max Range: 4.1973. Min Range: -4.1973

Max Act: 4.0097. Min Act: -0.1700

Data Index: 338129 (C4 (Web Text))

Max Activating Token Index: 344

Text #11

Max Range: 4.1973. Min Range: -4.1973

Max Act: 4.0097. Min Act: -0.1700

Data Index: 538038 (C4 (Web Text))

Max Activating Token Index: 237

Text #12

Max Range: 4.1973. Min Range: -4.1973

Max Act: 4.0097. Min Act: -0.1700

Data Index: 249666 (C4 (Web Text))

Max Activating Token Index: 856

Text #13

Max Range: 4.1973. Min Range: -4.1973

Max Act: 4.0097. Min Act: -0.1700

Data Index: 269284 (C4 (Web Text))

Max Activating Token Index: 388

Text #14

Max Range: 4.1973. Min Range: -4.1973

Max Act: 4.0097. Min Act: -0.1700

Data Index: 1053246 (C4 (Web Text))

Max Activating Token Index: 254

Text #15

Max Range: 4.1973. Min Range: -4.1973

Max Act: 3.9785. Min Act: -0.1700

Data Index: 475963 (C4 (Web Text))

Max Activating Token Index: 565

Text #16

Max Range: 4.1973. Min Range: -4.1973

Max Act: 3.9785. Min Act: -0.1700

Data Index: 171115 (C4 (Web Text))

Max Activating Token Index: 320

Text #17

Max Range: 4.1973. Min Range: -4.1973

Max Act: 3.9785. Min Act: -0.1700

Data Index: 1186780 (C4 (Web Text))

Max Activating Token Index: 17

Text #18

Max Range: 4.1973. Min Range: -4.1973

Max Act: 3.8846. Min Act: -0.1700

Data Index: 90600 (C4 (Web Text))

Max Activating Token Index: 931

Text #19

Max Range: 4.1973. Min Range: -4.1973

Max Act: 3.9159. Min Act: -0.1700

Data Index: 1039381 (C4 (Web Text))

Max Activating Token Index: 173