Model: GELU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 299 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-3l')

Text #0

Max Range: 3.1295. Min Range: -3.1295

Max Act: 3.1295. Min Act: -0.1700

Data Index: 912436 (C4 (Web Text))

Max Activating Token Index: 216

Text #1

Max Range: 3.1295. Min Range: -3.1295

Max Act: 3.0979. Min Act: -0.1700

Data Index: 849380 (C4 (Web Text))

Max Activating Token Index: 726

Text #2

Max Range: 3.1295. Min Range: -3.1295

Max Act: 3.0506. Min Act: -0.1700

Data Index: 47692 (C4 (Web Text))

Max Activating Token Index: 496

Text #3

Max Range: 3.1295. Min Range: -3.1295

Max Act: 3.0032. Min Act: -0.1700

Data Index: 692370 (C4 (Web Text))

Max Activating Token Index: 488

Text #4

Max Range: 3.1295. Min Range: -3.1295

Max Act: 3.0032. Min Act: -0.1700

Data Index: 744233 (C4 (Web Text))

Max Activating Token Index: 978

Text #5

Max Range: 3.1295. Min Range: -3.1295

Max Act: 2.9716. Min Act: -0.1700

Data Index: 589674 (C4 (Web Text))

Max Activating Token Index: 312

Text #6

Max Range: 3.1295. Min Range: -3.1295

Max Act: 2.9716. Min Act: -0.1700

Data Index: 671541 (C4 (Web Text))

Max Activating Token Index: 838

Text #7

Max Range: 3.1295. Min Range: -3.1295

Max Act: 2.9716. Min Act: -0.1700

Data Index: 1067618 (C4 (Web Text))

Max Activating Token Index: 24

Text #8

Max Range: 3.1295. Min Range: -3.1295

Max Act: 2.9557. Min Act: -0.1700

Data Index: 639383 (C4 (Web Text))

Max Activating Token Index: 732

Text #9

Max Range: 3.1295. Min Range: -3.1295

Max Act: 2.9716. Min Act: -0.1700

Data Index: 640312 (C4 (Web Text))

Max Activating Token Index: 664

Text #10

Max Range: 3.1295. Min Range: -3.1295

Max Act: 2.9557. Min Act: -0.1700

Data Index: 1190529 (C4 (Web Text))

Max Activating Token Index: 584

Text #11

Max Range: 3.1295. Min Range: -3.1295

Max Act: 2.9716. Min Act: -0.1700

Data Index: 408685 (C4 (Web Text))

Max Activating Token Index: 324

Text #12

Max Range: 3.1295. Min Range: -3.1295

Max Act: 2.9399. Min Act: -0.1700

Data Index: 464080 (C4 (Web Text))

Max Activating Token Index: 276

Text #13

Max Range: 3.1295. Min Range: -3.1295

Max Act: 2.9241. Min Act: -0.1700

Data Index: 987457 (C4 (Web Text))

Max Activating Token Index: 137

Text #14

Max Range: 3.1295. Min Range: -3.1295

Max Act: 2.9716. Min Act: -0.1700

Data Index: 1355548 (C4 (Web Text))

Max Activating Token Index: 883

Text #15

Max Range: 3.1295. Min Range: -3.1295

Max Act: 2.9399. Min Act: -0.1700

Data Index: 1214992 (C4 (Web Text))

Max Activating Token Index: 261

Text #16

Max Range: 3.1295. Min Range: -3.1295

Max Act: 2.9399. Min Act: -0.1700

Data Index: 219906 (C4 (Web Text))

Max Activating Token Index: 107

Text #17

Max Range: 3.1295. Min Range: -3.1295

Max Act: 2.9399. Min Act: -0.1700

Data Index: 608078 (C4 (Web Text))

Max Activating Token Index: 32

Text #18

Max Range: 3.1295. Min Range: -3.1295

Max Act: 2.9399. Min Act: -0.1700

Data Index: 1015662 (C4 (Web Text))

Max Activating Token Index: 5

Text #19

Max Range: 3.1295. Min Range: -3.1295

Max Act: 2.9082. Min Act: -0.1700

Data Index: 917038 (C4 (Web Text))

Max Activating Token Index: 27