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

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

Neuron 1667 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: 3.6139. Min Range: -3.6139

Max Act: 3.6139. Min Act: -0.1700

Data Index: 32721 (C4 (Web Text))

Max Activating Token Index: 296

Text #1

Max Range: 3.6139. Min Range: -3.6139

Max Act: 3.3732. Min Act: -0.1700

Data Index: 753107 (C4 (Web Text))

Max Activating Token Index: 623

Text #2

Max Range: 3.6139. Min Range: -3.6139

Max Act: 3.2968. Min Act: -0.1699

Data Index: 547382 (C4 (Web Text))

Max Activating Token Index: 682

Text #3

Max Range: 3.6139. Min Range: -3.6139

Max Act: 3.2797. Min Act: -0.1700

Data Index: 27612 (C4 (Web Text))

Max Activating Token Index: 130

Text #4

Max Range: 3.6139. Min Range: -3.6139

Max Act: 3.2802. Min Act: -0.1700

Data Index: 1079578 (C4 (Web Text))

Max Activating Token Index: 215

Text #5

Max Range: 3.6139. Min Range: -3.6139

Max Act: 3.2538. Min Act: -0.1700

Data Index: 378454 (C4 (Web Text))

Max Activating Token Index: 980

Text #6

Max Range: 3.6139. Min Range: -3.6139

Max Act: 3.2349. Min Act: -0.1700

Data Index: 893969 (C4 (Web Text))

Max Activating Token Index: 90

Text #7

Max Range: 3.6139. Min Range: -3.6139

Max Act: 3.1867. Min Act: -0.1700

Data Index: 1221935 (C4 (Web Text))

Max Activating Token Index: 606

Text #8

Max Range: 3.6139. Min Range: -3.6139

Max Act: 3.1841. Min Act: -0.1700

Data Index: 564123 (C4 (Web Text))

Max Activating Token Index: 272

Text #9

Max Range: 3.6139. Min Range: -3.6139

Max Act: 3.1927. Min Act: -0.1700

Data Index: 81677 (C4 (Web Text))

Max Activating Token Index: 645

Text #10

Max Range: 3.6139. Min Range: -3.6139

Max Act: 3.1892. Min Act: -0.1700

Data Index: 108068 (C4 (Web Text))

Max Activating Token Index: 56

Text #11

Max Range: 3.6139. Min Range: -3.6139

Max Act: 3.1726. Min Act: -0.1699

Data Index: 1238251 (C4 (Web Text))

Max Activating Token Index: 846

Text #12

Max Range: 3.6139. Min Range: -3.6139

Max Act: 3.1748. Min Act: -0.1700

Data Index: 6055 (C4 (Web Text))

Max Activating Token Index: 64

Text #13

Max Range: 3.6139. Min Range: -3.6139

Max Act: 3.1690. Min Act: -0.1700

Data Index: 517474 (C4 (Web Text))

Max Activating Token Index: 994

Text #14

Max Range: 3.6139. Min Range: -3.6139

Max Act: 3.1659. Min Act: -0.1700

Data Index: 1340212 (C4 (Web Text))

Max Activating Token Index: 710

Text #15

Max Range: 3.6139. Min Range: -3.6139

Max Act: 3.1531. Min Act: -0.1700

Data Index: 835533 (C4 (Web Text))

Max Activating Token Index: 597

Text #16

Max Range: 3.6139. Min Range: -3.6139

Max Act: 3.1514. Min Act: -0.1700

Data Index: 174210 (C4 (Web Text))

Max Activating Token Index: 535

Text #17

Max Range: 3.6139. Min Range: -3.6139

Max Act: 3.1643. Min Act: -0.1700

Data Index: 518867 (C4 (Web Text))

Max Activating Token Index: 578

Text #18

Max Range: 3.6139. Min Range: -3.6139

Max Act: 3.1598. Min Act: -0.1700

Data Index: 278661 (C4 (Web Text))

Max Activating Token Index: 260

Text #19

Max Range: 3.6139. Min Range: -3.6139

Max Act: 3.1623. Min Act: -0.1700

Data Index: 63867 (C4 (Web Text))

Max Activating Token Index: 400