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

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

Neuron 1295 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: 4.1992. Min Range: -4.1992

Max Act: 4.1992. Min Act: -0.1700

Data Index: 559187 (C4 (Web Text))

Max Activating Token Index: 611

Text #1

Max Range: 4.1992. Min Range: -4.1992

Max Act: 4.1680. Min Act: -0.1700

Data Index: 246921 (C4 (Web Text))

Max Activating Token Index: 199

Text #2

Max Range: 4.1992. Min Range: -4.1992

Max Act: 4.0273. Min Act: -0.1700

Data Index: 730115 (C4 (Web Text))

Max Activating Token Index: 316

Text #3

Max Range: 4.1992. Min Range: -4.1992

Max Act: 4.0117. Min Act: -0.1700

Data Index: 547371 (C4 (Web Text))

Max Activating Token Index: 550

Text #4

Max Range: 4.1992. Min Range: -4.1992

Max Act: 3.9960. Min Act: -0.1700

Data Index: 679868 (C4 (Web Text))

Max Activating Token Index: 280

Text #5

Max Range: 4.1992. Min Range: -4.1992

Max Act: 3.9491. Min Act: -0.1700

Data Index: 1343545 (C4 (Web Text))

Max Activating Token Index: 41

Text #6

Max Range: 4.1992. Min Range: -4.1992

Max Act: 3.9335. Min Act: -0.1697

Data Index: 797927 (C4 (Web Text))

Max Activating Token Index: 321

Text #7

Max Range: 4.1992. Min Range: -4.1992

Max Act: 4.0429. Min Act: -0.1700

Data Index: 657112 (C4 (Web Text))

Max Activating Token Index: 354

Text #8

Max Range: 4.1992. Min Range: -4.1992

Max Act: 3.9022. Min Act: -0.1700

Data Index: 782074 (C4 (Web Text))

Max Activating Token Index: 71

Text #9

Max Range: 4.1992. Min Range: -4.1992

Max Act: 3.9022. Min Act: -0.1700

Data Index: 347280 (C4 (Web Text))

Max Activating Token Index: 502

Text #10

Max Range: 4.1992. Min Range: -4.1992

Max Act: 3.9022. Min Act: -0.1700

Data Index: 1303273 (C4 (Web Text))

Max Activating Token Index: 547

Text #11

Max Range: 4.1992. Min Range: -4.1992

Max Act: 3.9179. Min Act: -0.1700

Data Index: 604746 (C4 (Web Text))

Max Activating Token Index: 521

Text #12

Max Range: 4.1992. Min Range: -4.1992

Max Act: 3.9179. Min Act: -0.1700

Data Index: 1253698 (C4 (Web Text))

Max Activating Token Index: 43

Text #13

Max Range: 4.1992. Min Range: -4.1992

Max Act: 3.8397. Min Act: -0.1700

Data Index: 583410 (C4 (Web Text))

Max Activating Token Index: 68

Text #14

Max Range: 4.1992. Min Range: -4.1992

Max Act: 3.8553. Min Act: -0.1700

Data Index: 864568 (C4 (Web Text))

Max Activating Token Index: 286

Text #15

Max Range: 4.1992. Min Range: -4.1992

Max Act: 3.8710. Min Act: -0.1700

Data Index: 1141971 (C4 (Web Text))

Max Activating Token Index: 668

Text #16

Max Range: 4.1992. Min Range: -4.1992

Max Act: 3.8397. Min Act: -0.1698

Data Index: 196442 (C4 (Web Text))

Max Activating Token Index: 196

Text #17

Max Range: 4.1992. Min Range: -4.1992

Max Act: 3.9022. Min Act: -0.1700

Data Index: 412586 (C4 (Web Text))

Max Activating Token Index: 499

Text #18

Max Range: 4.1992. Min Range: -4.1992

Max Act: 3.8710. Min Act: -0.1700

Data Index: 1068972 (C4 (Web Text))

Max Activating Token Index: 425

Text #19

Max Range: 4.1992. Min Range: -4.1992

Max Act: 3.7928. Min Act: -0.1700

Data Index: 47630 (C4 (Web Text))

Max Activating Token Index: 251