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

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

Neuron 1700 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: 5.9430. Min Range: -5.9430

Max Act: 5.9430. Min Act: -0.1700

Data Index: 361479 (C4 (Web Text))

Max Activating Token Index: 448

Text #1

Max Range: 5.9430. Min Range: -5.9430

Max Act: 5.7555. Min Act: -0.1700

Data Index: 1314191 (C4 (Web Text))

Max Activating Token Index: 607

Text #2

Max Range: 5.9430. Min Range: -5.9430

Max Act: 5.8493. Min Act: -0.1700

Data Index: 635304 (C4 (Web Text))

Max Activating Token Index: 484

Text #3

Max Range: 5.9430. Min Range: -5.9430

Max Act: 5.7868. Min Act: -0.1700

Data Index: 852735 (C4 (Web Text))

Max Activating Token Index: 330

Text #4

Max Range: 5.9430. Min Range: -5.9430

Max Act: 5.8180. Min Act: -0.1700

Data Index: 385550 (C4 (Web Text))

Max Activating Token Index: 537

Text #5

Max Range: 5.9430. Min Range: -5.9430

Max Act: 5.9118. Min Act: -0.1700

Data Index: 97910 (C4 (Web Text))

Max Activating Token Index: 927

Text #6

Max Range: 5.9430. Min Range: -5.9430

Max Act: 5.6618. Min Act: -0.1700

Data Index: 803593 (C4 (Web Text))

Max Activating Token Index: 260

Text #7

Max Range: 5.9430. Min Range: -5.9430

Max Act: 5.8180. Min Act: -0.1700

Data Index: 444141 (C4 (Web Text))

Max Activating Token Index: 362

Text #8

Max Range: 5.9430. Min Range: -5.9430

Max Act: 5.7243. Min Act: -0.1700

Data Index: 566252 (C4 (Web Text))

Max Activating Token Index: 358

Text #9

Max Range: 5.9430. Min Range: -5.9430

Max Act: 5.7243. Min Act: -0.1700

Data Index: 1321590 (C4 (Web Text))

Max Activating Token Index: 246

Text #10

Max Range: 5.9430. Min Range: -5.9430

Max Act: 5.7555. Min Act: -0.1700

Data Index: 1080014 (C4 (Web Text))

Max Activating Token Index: 274

Text #11

Max Range: 5.9430. Min Range: -5.9430

Max Act: 5.7555. Min Act: -0.1700

Data Index: 721262 (C4 (Web Text))

Max Activating Token Index: 255

Text #12

Max Range: 5.9430. Min Range: -5.9430

Max Act: 5.7243. Min Act: -0.1700

Data Index: 854313 (C4 (Web Text))

Max Activating Token Index: 361

Text #13

Max Range: 5.9430. Min Range: -5.9430

Max Act: 5.7243. Min Act: -0.1700

Data Index: 357880 (C4 (Web Text))

Max Activating Token Index: 151

Text #14

Max Range: 5.9430. Min Range: -5.9430

Max Act: 5.7243. Min Act: -0.1700

Data Index: 313023 (C4 (Web Text))

Max Activating Token Index: 230

Text #15

Max Range: 5.9430. Min Range: -5.9430

Max Act: 5.6305. Min Act: -0.1700

Data Index: 12098 (C4 (Web Text))

Max Activating Token Index: 91

Text #16

Max Range: 5.9430. Min Range: -5.9430

Max Act: 5.6305. Min Act: -0.1700

Data Index: 811119 (C4 (Web Text))

Max Activating Token Index: 707

Text #17

Max Range: 5.9430. Min Range: -5.9430

Max Act: 5.6305. Min Act: -0.1700

Data Index: 435956 (C4 (Web Text))

Max Activating Token Index: 468

Text #18

Max Range: 5.9430. Min Range: -5.9430

Max Act: 5.6305. Min Act: -0.1700

Data Index: 760208 (C4 (Web Text))

Max Activating Token Index: 372

Text #19

Max Range: 5.9430. Min Range: -5.9430

Max Act: 5.7868. Min Act: -0.1700

Data Index: 161827 (C4 (Web Text))

Max Activating Token Index: 787