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

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

Neuron 691 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')

Text #0

Max Range: 7.3042. Min Range: -7.3042

Max Act: 7.2417. Min Act: -0.1700

Data Index: 586237 (C4 (Web Text))

Max Activating Token Index: 421

Text #1

Max Range: 7.3042. Min Range: -7.3042

Max Act: 7.3042. Min Act: -0.1700

Data Index: 901516 (C4 (Web Text))

Max Activating Token Index: 480

Text #2

Max Range: 7.3042. Min Range: -7.3042

Max Act: 7.1167. Min Act: -0.1700

Data Index: 1013485 (C4 (Web Text))

Max Activating Token Index: 161

Text #3

Max Range: 7.3042. Min Range: -7.3042

Max Act: 7.1792. Min Act: -0.1700

Data Index: 1068504 (C4 (Web Text))

Max Activating Token Index: 485

Text #4

Max Range: 7.3042. Min Range: -7.3042

Max Act: 7.2417. Min Act: -0.1700

Data Index: 70189 (C4 (Web Text))

Max Activating Token Index: 100

Text #5

Max Range: 7.3042. Min Range: -7.3042

Max Act: 7.0542. Min Act: -0.1700

Data Index: 39327 (C4 (Web Text))

Max Activating Token Index: 478

Text #6

Max Range: 7.3042. Min Range: -7.3042

Max Act: 7.2417. Min Act: -0.1700

Data Index: 1189474 (C4 (Web Text))

Max Activating Token Index: 167

Text #7

Max Range: 7.3042. Min Range: -7.3042

Max Act: 6.9917. Min Act: -0.1700

Data Index: 714861 (C4 (Web Text))

Max Activating Token Index: 305

Text #8

Max Range: 7.3042. Min Range: -7.3042

Max Act: 6.9917. Min Act: -0.1700

Data Index: 529724 (C4 (Web Text))

Max Activating Token Index: 725

Text #9

Max Range: 7.3042. Min Range: -7.3042

Max Act: 7.1167. Min Act: -0.1700

Data Index: 195815 (C4 (Web Text))

Max Activating Token Index: 663

Text #10

Max Range: 7.3042. Min Range: -7.3042

Max Act: 7.0854. Min Act: -0.1700

Data Index: 185656 (C4 (Web Text))

Max Activating Token Index: 683

Text #11

Max Range: 7.3042. Min Range: -7.3042

Max Act: 7.0542. Min Act: -0.1700

Data Index: 833488 (C4 (Web Text))

Max Activating Token Index: 332

Text #12

Max Range: 7.3042. Min Range: -7.3042

Max Act: 6.9917. Min Act: -0.1700

Data Index: 1442128 (Python Code)

Max Activating Token Index: 465

Text #13

Max Range: 7.3042. Min Range: -7.3042

Max Act: 7.0542. Min Act: -0.1700

Data Index: 1145133 (C4 (Web Text))

Max Activating Token Index: 685

Text #14

Max Range: 7.3042. Min Range: -7.3042

Max Act: 6.9917. Min Act: -0.1700

Data Index: 436694 (C4 (Web Text))

Max Activating Token Index: 155

Text #15

Max Range: 7.3042. Min Range: -7.3042

Max Act: 6.9917. Min Act: -0.1700

Data Index: 1114085 (C4 (Web Text))

Max Activating Token Index: 113

Text #16

Max Range: 7.3042. Min Range: -7.3042

Max Act: 7.0542. Min Act: -0.1700

Data Index: 802175 (C4 (Web Text))

Max Activating Token Index: 546

Text #17

Max Range: 7.3042. Min Range: -7.3042

Max Act: 6.9917. Min Act: -0.1700

Data Index: 1254065 (C4 (Web Text))

Max Activating Token Index: 424

Text #18

Max Range: 7.3042. Min Range: -7.3042

Max Act: 6.8979. Min Act: -0.1700

Data Index: 362481 (C4 (Web Text))

Max Activating Token Index: 780

Text #19

Max Range: 7.3042. Min Range: -7.3042

Max Act: 7.1479. Min Act: -0.1700

Data Index: 25167 (C4 (Web Text))

Max Activating Token Index: 623