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

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

Neuron 1747 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: 7.6409. Min Range: -7.6409

Max Act: 7.6409. Min Act: -0.1700

Data Index: 575691 (C4 (Web Text))

Max Activating Token Index: 373

Text #1

Max Range: 7.6409. Min Range: -7.6409

Max Act: 7.3909. Min Act: -0.1700

Data Index: 397327 (C4 (Web Text))

Max Activating Token Index: 25

Text #2

Max Range: 7.6409. Min Range: -7.6409

Max Act: 7.4534. Min Act: -0.1697

Data Index: 600160 (C4 (Web Text))

Max Activating Token Index: 810

Text #3

Max Range: 7.6409. Min Range: -7.6409

Max Act: 7.3284. Min Act: -0.1700

Data Index: 478421 (C4 (Web Text))

Max Activating Token Index: 719

Text #4

Max Range: 7.6409. Min Range: -7.6409

Max Act: 7.3284. Min Act: -0.1700

Data Index: 801007 (C4 (Web Text))

Max Activating Token Index: 125

Text #5

Max Range: 7.6409. Min Range: -7.6409

Max Act: 7.1409. Min Act: -0.1700

Data Index: 578098 (C4 (Web Text))

Max Activating Token Index: 654

Text #6

Max Range: 7.6409. Min Range: -7.6409

Max Act: 7.1409. Min Act: -0.1694

Data Index: 628344 (C4 (Web Text))

Max Activating Token Index: 852

Text #7

Max Range: 7.6409. Min Range: -7.6409

Max Act: 7.0159. Min Act: -0.1700

Data Index: 290674 (C4 (Web Text))

Max Activating Token Index: 299

Text #8

Max Range: 7.6409. Min Range: -7.6409

Max Act: 7.0784. Min Act: -0.1700

Data Index: 274863 (C4 (Web Text))

Max Activating Token Index: 92

Text #9

Max Range: 7.6409. Min Range: -7.6409

Max Act: 6.9534. Min Act: -0.1676

Data Index: 48894 (C4 (Web Text))

Max Activating Token Index: 229

Text #10

Max Range: 7.6409. Min Range: -7.6409

Max Act: 6.9534. Min Act: -0.1700

Data Index: 1275722 (C4 (Web Text))

Max Activating Token Index: 150

Text #11

Max Range: 7.6409. Min Range: -7.6409

Max Act: 7.0159. Min Act: -0.1700

Data Index: 835958 (C4 (Web Text))

Max Activating Token Index: 40

Text #12

Max Range: 7.6409. Min Range: -7.6409

Max Act: 6.8909. Min Act: -0.1700

Data Index: 856112 (C4 (Web Text))

Max Activating Token Index: 232

Text #13

Max Range: 7.6409. Min Range: -7.6409

Max Act: 6.8284. Min Act: -0.1700

Data Index: 912001 (C4 (Web Text))

Max Activating Token Index: 652

Text #14

Max Range: 7.6409. Min Range: -7.6409

Max Act: 6.7659. Min Act: -0.1700

Data Index: 96022 (C4 (Web Text))

Max Activating Token Index: 448

Text #15

Max Range: 7.6409. Min Range: -7.6409

Max Act: 6.7659. Min Act: -0.1699

Data Index: 1358672 (C4 (Web Text))

Max Activating Token Index: 436

Text #16

Max Range: 7.6409. Min Range: -7.6409

Max Act: 6.7659. Min Act: -0.1696

Data Index: 853749 (C4 (Web Text))

Max Activating Token Index: 167

Text #17

Max Range: 7.6409. Min Range: -7.6409

Max Act: 6.7659. Min Act: -0.1699

Data Index: 993044 (C4 (Web Text))

Max Activating Token Index: 141

Text #18

Max Range: 7.6409. Min Range: -7.6409

Max Act: 6.8284. Min Act: -0.1700

Data Index: 343312 (C4 (Web Text))

Max Activating Token Index: 710

Text #19

Max Range: 7.6409. Min Range: -7.6409

Max Act: 6.7034. Min Act: -0.1700

Data Index: 741177 (C4 (Web Text))

Max Activating Token Index: 102