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

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

Neuron 459 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: 3.0118. Min Range: -3.0118

Max Act: 3.0118. Min Act: -0.1700

Data Index: 1200752 (C4 (Web Text))

Max Activating Token Index: 780

Text #1

Max Range: 3.0118. Min Range: -3.0118

Max Act: 2.9495. Min Act: -0.1700

Data Index: 1450439 (Python Code)

Max Activating Token Index: 345

Text #2

Max Range: 3.0118. Min Range: -3.0118

Max Act: 2.9085. Min Act: -0.1699

Data Index: 1552235 (Python Code)

Max Activating Token Index: 765

Text #3

Max Range: 3.0118. Min Range: -3.0118

Max Act: 2.8849. Min Act: -0.1700

Data Index: 1406234 (Python Code)

Max Activating Token Index: 281

Text #4

Max Range: 3.0118. Min Range: -3.0118

Max Act: 2.8843. Min Act: -0.1700

Data Index: 1592123 (Python Code)

Max Activating Token Index: 637

Text #5

Max Range: 3.0118. Min Range: -3.0118

Max Act: 2.8732. Min Act: -0.1700

Data Index: 1452642 (Python Code)

Max Activating Token Index: 608

Text #6

Max Range: 3.0118. Min Range: -3.0118

Max Act: 2.8551. Min Act: -0.1700

Data Index: 1504531 (Python Code)

Max Activating Token Index: 185

Text #7

Max Range: 3.0118. Min Range: -3.0118

Max Act: 2.8553. Min Act: -0.1700

Data Index: 1639447 (Python Code)

Max Activating Token Index: 416

Text #8

Max Range: 3.0118. Min Range: -3.0118

Max Act: 2.8409. Min Act: -0.1700

Data Index: 1383895 (Python Code)

Max Activating Token Index: 641

Text #9

Max Range: 3.0118. Min Range: -3.0118

Max Act: 2.8505. Min Act: -0.1700

Data Index: 1633418 (Python Code)

Max Activating Token Index: 829

Text #10

Max Range: 3.0118. Min Range: -3.0118

Max Act: 2.8330. Min Act: -0.1700

Data Index: 1481763 (Python Code)

Max Activating Token Index: 76

Text #11

Max Range: 3.0118. Min Range: -3.0118

Max Act: 2.8386. Min Act: -0.1699

Data Index: 1509364 (Python Code)

Max Activating Token Index: 741

Text #12

Max Range: 3.0118. Min Range: -3.0118

Max Act: 2.8106. Min Act: -0.1700

Data Index: 1445950 (Python Code)

Max Activating Token Index: 496

Text #13

Max Range: 3.0118. Min Range: -3.0118

Max Act: 2.8192. Min Act: -0.1700

Data Index: 1409335 (Python Code)

Max Activating Token Index: 585

Text #14

Max Range: 3.0118. Min Range: -3.0118

Max Act: 2.8176. Min Act: -0.1700

Data Index: 1409647 (Python Code)

Max Activating Token Index: 967

Text #15

Max Range: 3.0118. Min Range: -3.0118

Max Act: 2.8087. Min Act: -0.1700

Data Index: 1538659 (Python Code)

Max Activating Token Index: 565

Text #16

Max Range: 3.0118. Min Range: -3.0118

Max Act: 2.7940. Min Act: -0.1700

Data Index: 1501862 (Python Code)

Max Activating Token Index: 740

Text #17

Max Range: 3.0118. Min Range: -3.0118

Max Act: 2.7785. Min Act: -0.1700

Data Index: 1418576 (Python Code)

Max Activating Token Index: 196

Text #18

Max Range: 3.0118. Min Range: -3.0118

Max Act: 2.7876. Min Act: -0.1700

Data Index: 1495248 (Python Code)

Max Activating Token Index: 724

Text #19

Max Range: 3.0118. Min Range: -3.0118

Max Act: 2.7824. Min Act: -0.1700

Data Index: 1435294 (Python Code)

Max Activating Token Index: 268