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

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

Neuron 910 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: 6.1167. Min Range: -6.1167

Max Act: 6.1167. Min Act: -0.1700

Data Index: 151923 (C4 (Web Text))

Max Activating Token Index: 447

Text #1

Max Range: 6.1167. Min Range: -6.1167

Max Act: 6.0855. Min Act: -0.1700

Data Index: 449422 (C4 (Web Text))

Max Activating Token Index: 496

Text #2

Max Range: 6.1167. Min Range: -6.1167

Max Act: 6.0230. Min Act: -0.1700

Data Index: 575996 (C4 (Web Text))

Max Activating Token Index: 588

Text #3

Max Range: 6.1167. Min Range: -6.1167

Max Act: 5.9292. Min Act: -0.1700

Data Index: 1233744 (C4 (Web Text))

Max Activating Token Index: 301

Text #4

Max Range: 6.1167. Min Range: -6.1167

Max Act: 5.8980. Min Act: -0.1700

Data Index: 306150 (C4 (Web Text))

Max Activating Token Index: 834

Text #5

Max Range: 6.1167. Min Range: -6.1167

Max Act: 5.9292. Min Act: -0.1700

Data Index: 751841 (C4 (Web Text))

Max Activating Token Index: 808

Text #6

Max Range: 6.1167. Min Range: -6.1167

Max Act: 5.7417. Min Act: -0.1700

Data Index: 793454 (C4 (Web Text))

Max Activating Token Index: 987

Text #7

Max Range: 6.1167. Min Range: -6.1167

Max Act: 5.7730. Min Act: -0.1700

Data Index: 216865 (C4 (Web Text))

Max Activating Token Index: 871

Text #8

Max Range: 6.1167. Min Range: -6.1167

Max Act: 5.4292. Min Act: -0.1700

Data Index: 554708 (C4 (Web Text))

Max Activating Token Index: 941

Text #9

Max Range: 6.1167. Min Range: -6.1167

Max Act: 5.3980. Min Act: -0.1700

Data Index: 10394 (C4 (Web Text))

Max Activating Token Index: 520

Text #10

Max Range: 6.1167. Min Range: -6.1167

Max Act: 5.3042. Min Act: -0.1700

Data Index: 761277 (C4 (Web Text))

Max Activating Token Index: 230

Text #11

Max Range: 6.1167. Min Range: -6.1167

Max Act: 5.3042. Min Act: -0.1700

Data Index: 850578 (C4 (Web Text))

Max Activating Token Index: 697

Text #12

Max Range: 6.1167. Min Range: -6.1167

Max Act: 5.3042. Min Act: -0.1700

Data Index: 198967 (C4 (Web Text))

Max Activating Token Index: 708

Text #13

Max Range: 6.1167. Min Range: -6.1167

Max Act: 5.2730. Min Act: -0.1700

Data Index: 450310 (C4 (Web Text))

Max Activating Token Index: 163

Text #14

Max Range: 6.1167. Min Range: -6.1167

Max Act: 5.2730. Min Act: -0.1700

Data Index: 1271906 (C4 (Web Text))

Max Activating Token Index: 981

Text #15

Max Range: 6.1167. Min Range: -6.1167

Max Act: 5.2417. Min Act: -0.1700

Data Index: 835529 (C4 (Web Text))

Max Activating Token Index: 157

Text #16

Max Range: 6.1167. Min Range: -6.1167

Max Act: 5.1792. Min Act: -0.1700

Data Index: 511346 (C4 (Web Text))

Max Activating Token Index: 393

Text #17

Max Range: 6.1167. Min Range: -6.1167

Max Act: 5.2417. Min Act: -0.1700

Data Index: 48380 (C4 (Web Text))

Max Activating Token Index: 745

Text #18

Max Range: 6.1167. Min Range: -6.1167

Max Act: 5.2105. Min Act: -0.1700

Data Index: 239201 (C4 (Web Text))

Max Activating Token Index: 362

Text #19

Max Range: 6.1167. Min Range: -6.1167

Max Act: 5.2105. Min Act: -0.1700

Data Index: 585198 (C4 (Web Text))

Max Activating Token Index: 10