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

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

Neuron 1637 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: 3.6723. Min Range: -3.6723

Max Act: 3.6484. Min Act: -0.1700

Data Index: 1389127 (Python Code)

Max Activating Token Index: 732

Text #1

Max Range: 3.6723. Min Range: -3.6723

Max Act: 3.6723. Min Act: -0.1700

Data Index: 1214942 (C4 (Web Text))

Max Activating Token Index: 265

Text #2

Max Range: 3.6723. Min Range: -3.6723

Max Act: 3.5244. Min Act: -0.1700

Data Index: 938990 (C4 (Web Text))

Max Activating Token Index: 387

Text #3

Max Range: 3.6723. Min Range: -3.6723

Max Act: 3.5254. Min Act: -0.1700

Data Index: 1351376 (C4 (Web Text))

Max Activating Token Index: 831

Text #4

Max Range: 3.6723. Min Range: -3.6723

Max Act: 3.4810. Min Act: -0.1700

Data Index: 1390788 (Python Code)

Max Activating Token Index: 333

Text #5

Max Range: 3.6723. Min Range: -3.6723

Max Act: 3.4678. Min Act: -0.1700

Data Index: 36548 (C4 (Web Text))

Max Activating Token Index: 570

Text #6

Max Range: 3.6723. Min Range: -3.6723

Max Act: 3.4581. Min Act: -0.1700

Data Index: 533390 (C4 (Web Text))

Max Activating Token Index: 63

Text #7

Max Range: 3.6723. Min Range: -3.6723

Max Act: 3.4659. Min Act: -0.1700

Data Index: 246171 (C4 (Web Text))

Max Activating Token Index: 98

Text #8

Max Range: 3.6723. Min Range: -3.6723

Max Act: 3.4399. Min Act: -0.1700

Data Index: 1501006 (Python Code)

Max Activating Token Index: 467

Text #9

Max Range: 3.6723. Min Range: -3.6723

Max Act: 3.4554. Min Act: -0.1700

Data Index: 883981 (C4 (Web Text))

Max Activating Token Index: 440

Text #10

Max Range: 3.6723. Min Range: -3.6723

Max Act: 3.4582. Min Act: -0.1700

Data Index: 162905 (C4 (Web Text))

Max Activating Token Index: 696

Text #11

Max Range: 3.6723. Min Range: -3.6723

Max Act: 3.4354. Min Act: -0.1700

Data Index: 1007951 (C4 (Web Text))

Max Activating Token Index: 881

Text #12

Max Range: 3.6723. Min Range: -3.6723

Max Act: 3.4290. Min Act: -0.1700

Data Index: 1211025 (C4 (Web Text))

Max Activating Token Index: 828

Text #13

Max Range: 3.6723. Min Range: -3.6723

Max Act: 3.4105. Min Act: -0.1700

Data Index: 777676 (C4 (Web Text))

Max Activating Token Index: 495

Text #14

Max Range: 3.6723. Min Range: -3.6723

Max Act: 3.4262. Min Act: -0.1700

Data Index: 604171 (C4 (Web Text))

Max Activating Token Index: 88

Text #15

Max Range: 3.6723. Min Range: -3.6723

Max Act: 3.4591. Min Act: -0.1700

Data Index: 15405 (C4 (Web Text))

Max Activating Token Index: 612

Text #16

Max Range: 3.6723. Min Range: -3.6723

Max Act: 3.4162. Min Act: -0.1700

Data Index: 1301959 (C4 (Web Text))

Max Activating Token Index: 539

Text #17

Max Range: 3.6723. Min Range: -3.6723

Max Act: 3.4088. Min Act: -0.1700

Data Index: 356853 (C4 (Web Text))

Max Activating Token Index: 375

Text #18

Max Range: 3.6723. Min Range: -3.6723

Max Act: 3.4428. Min Act: -0.1700

Data Index: 190007 (C4 (Web Text))

Max Activating Token Index: 738

Text #19

Max Range: 3.6723. Min Range: -3.6723

Max Act: 3.4030. Min Act: -0.1700

Data Index: 582747 (C4 (Web Text))

Max Activating Token Index: 845