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

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

Neuron 2009 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: 5.6979. Min Range: -5.6979

Max Act: 5.6979. Min Act: -0.1700

Data Index: 113549 (C4 (Web Text))

Max Activating Token Index: 105

Text #1

Max Range: 5.6979. Min Range: -5.6979

Max Act: 5.6354. Min Act: -0.1700

Data Index: 1264250 (C4 (Web Text))

Max Activating Token Index: 215

Text #2

Max Range: 5.6979. Min Range: -5.6979

Max Act: 5.6666. Min Act: -0.1700

Data Index: 751567 (C4 (Web Text))

Max Activating Token Index: 259

Text #3

Max Range: 5.6979. Min Range: -5.6979

Max Act: 5.6666. Min Act: -0.1700

Data Index: 939023 (C4 (Web Text))

Max Activating Token Index: 175

Text #4

Max Range: 5.6979. Min Range: -5.6979

Max Act: 5.6354. Min Act: -0.1700

Data Index: 594636 (C4 (Web Text))

Max Activating Token Index: 208

Text #5

Max Range: 5.6979. Min Range: -5.6979

Max Act: 5.6354. Min Act: -0.1700

Data Index: 66368 (C4 (Web Text))

Max Activating Token Index: 99

Text #6

Max Range: 5.6979. Min Range: -5.6979

Max Act: 5.6666. Min Act: -0.1700

Data Index: 985047 (C4 (Web Text))

Max Activating Token Index: 435

Text #7

Max Range: 5.6979. Min Range: -5.6979

Max Act: 5.6041. Min Act: -0.1700

Data Index: 1290824 (C4 (Web Text))

Max Activating Token Index: 413

Text #8

Max Range: 5.6979. Min Range: -5.6979

Max Act: 5.6354. Min Act: -0.1700

Data Index: 1228282 (C4 (Web Text))

Max Activating Token Index: 98

Text #9

Max Range: 5.6979. Min Range: -5.6979

Max Act: 5.6354. Min Act: -0.1700

Data Index: 336189 (C4 (Web Text))

Max Activating Token Index: 216

Text #10

Max Range: 5.6979. Min Range: -5.6979

Max Act: 5.5729. Min Act: -0.1700

Data Index: 1172069 (C4 (Web Text))

Max Activating Token Index: 210

Text #11

Max Range: 5.6979. Min Range: -5.6979

Max Act: 5.6041. Min Act: -0.1700

Data Index: 297276 (C4 (Web Text))

Max Activating Token Index: 368

Text #12

Max Range: 5.6979. Min Range: -5.6979

Max Act: 5.6041. Min Act: -0.1700

Data Index: 1028625 (C4 (Web Text))

Max Activating Token Index: 323

Text #13

Max Range: 5.6979. Min Range: -5.6979

Max Act: 5.6041. Min Act: -0.1700

Data Index: 472652 (C4 (Web Text))

Max Activating Token Index: 123

Text #14

Max Range: 5.6979. Min Range: -5.6979

Max Act: 5.6041. Min Act: -0.1700

Data Index: 375567 (C4 (Web Text))

Max Activating Token Index: 695

Text #15

Max Range: 5.6979. Min Range: -5.6979

Max Act: 5.5416. Min Act: -0.1700

Data Index: 1032266 (C4 (Web Text))

Max Activating Token Index: 580

Text #16

Max Range: 5.6979. Min Range: -5.6979

Max Act: 5.5416. Min Act: -0.1700

Data Index: 775058 (C4 (Web Text))

Max Activating Token Index: 410

Text #17

Max Range: 5.6979. Min Range: -5.6979

Max Act: 5.5729. Min Act: -0.1700

Data Index: 472908 (C4 (Web Text))

Max Activating Token Index: 390

Text #18

Max Range: 5.6979. Min Range: -5.6979

Max Act: 5.5729. Min Act: -0.1700

Data Index: 531902 (C4 (Web Text))

Max Activating Token Index: 131

Text #19

Max Range: 5.6979. Min Range: -5.6979

Max Act: 5.5729. Min Act: -0.1700

Data Index: 533055 (C4 (Web Text))

Max Activating Token Index: 315