Model: GELU Model: 1 Layers, 2048 Neurons per Layer

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

Neuron 70 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Hooked Transformer Loading: HookedTransformer.from_pretrained('gelu-1l')

Click the toggle to see the full text!

Text #0

Max Range: 4.8330. Min Range: -4.8330

Max Act: 4.8330. Min Act: -0.1699

Data Index: 1357738 (C4 (Web Text))

Max Activating Token Index: 426

Text #1

Max Range: 4.8330. Min Range: -4.8330

Max Act: 4.7939. Min Act: -0.1696

Data Index: 1579504 (Python Code)

Max Activating Token Index: 253

Text #2

Max Range: 4.8330. Min Range: -4.8330

Max Act: 4.7167. Min Act: -0.1314

Data Index: 1541693 (Python Code)

Max Activating Token Index: 613

Text #3

Max Range: 4.8330. Min Range: -4.8330

Max Act: 4.7147. Min Act: -0.1224

Data Index: 1589009 (Python Code)

Max Activating Token Index: 664

Text #4

Max Range: 4.8330. Min Range: -4.8330

Max Act: 4.7274. Min Act: -0.1700

Data Index: 1632555 (Python Code)

Max Activating Token Index: 326

Text #5

Max Range: 4.8330. Min Range: -4.8330

Max Act: 4.7136. Min Act: -0.1324

Data Index: 1511081 (Python Code)

Max Activating Token Index: 150

Text #6

Max Range: 4.8330. Min Range: -4.8330

Max Act: 4.6753. Min Act: -0.1670

Data Index: 1614434 (Python Code)

Max Activating Token Index: 726

Text #7

Max Range: 4.8330. Min Range: -4.8330

Max Act: 4.6626. Min Act: -0.1700

Data Index: 1402507 (Python Code)

Max Activating Token Index: 788

Text #8

Max Range: 4.8330. Min Range: -4.8330

Max Act: 4.6086. Min Act: -0.1634

Data Index: 1617202 (Python Code)

Max Activating Token Index: 252

Text #9

Max Range: 4.8330. Min Range: -4.8330

Max Act: 4.6300. Min Act: -0.1243

Data Index: 1508673 (Python Code)

Max Activating Token Index: 537

Text #10

Max Range: 4.8330. Min Range: -4.8330

Max Act: 4.5981. Min Act: -0.1699

Data Index: 1382074 (Python Code)

Max Activating Token Index: 135

Text #11

Max Range: 4.8330. Min Range: -4.8330

Max Act: 4.5957. Min Act: -0.1700

Data Index: 1415586 (Python Code)

Max Activating Token Index: 974

Text #12

Max Range: 4.8330. Min Range: -4.8330

Max Act: 4.5640. Min Act: -0.1697

Data Index: 900551 (C4 (Web Text))

Max Activating Token Index: 96

Text #13

Max Range: 4.8330. Min Range: -4.8330

Max Act: 4.5581. Min Act: -0.1699

Data Index: 1452743 (Python Code)

Max Activating Token Index: 745

Text #14

Max Range: 4.8330. Min Range: -4.8330

Max Act: 4.5840. Min Act: -0.1224

Data Index: 1642515 (Python Code)

Max Activating Token Index: 569

Text #15

Max Range: 4.8330. Min Range: -4.8330

Max Act: 4.5777. Min Act: -0.1695

Data Index: 1654201 (Python Code)

Max Activating Token Index: 722

Text #16

Max Range: 4.8330. Min Range: -4.8330

Max Act: 4.5468. Min Act: -0.1651

Data Index: 1464886 (Python Code)

Max Activating Token Index: 49

Text #17

Max Range: 4.8330. Min Range: -4.8330

Max Act: 4.5442. Min Act: -0.1224

Data Index: 1482715 (Python Code)

Max Activating Token Index: 327

Text #18

Max Range: 4.8330. Min Range: -4.8330

Max Act: 4.5352. Min Act: -0.1224

Data Index: 1554900 (Python Code)

Max Activating Token Index: 263

Text #19

Max Range: 4.8330. Min Range: -4.8330

Max Act: 4.5480. Min Act: -0.1694

Data Index: 1536066 (Python Code)

Max Activating Token Index: 536