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

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

Neuron 1716 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: 3.5188. Min Range: -3.5188

Max Act: 3.5188. Min Act: -0.1700

Data Index: 397482 (C4 (Web Text))

Max Activating Token Index: 402

Text #1

Max Range: 3.5188. Min Range: -3.5188

Max Act: 3.4875. Min Act: -0.1700

Data Index: 258675 (C4 (Web Text))

Max Activating Token Index: 468

Text #2

Max Range: 3.5188. Min Range: -3.5188

Max Act: 3.4561. Min Act: -0.1700

Data Index: 862918 (C4 (Web Text))

Max Activating Token Index: 332

Text #3

Max Range: 3.5188. Min Range: -3.5188

Max Act: 3.4875. Min Act: -0.1700

Data Index: 506699 (C4 (Web Text))

Max Activating Token Index: 290

Text #4

Max Range: 3.5188. Min Range: -3.5188

Max Act: 3.4875. Min Act: -0.1700

Data Index: 1210764 (C4 (Web Text))

Max Activating Token Index: 929

Text #5

Max Range: 3.5188. Min Range: -3.5188

Max Act: 3.4561. Min Act: -0.1700

Data Index: 1014692 (C4 (Web Text))

Max Activating Token Index: 622

Text #6

Max Range: 3.5188. Min Range: -3.5188

Max Act: 3.4561. Min Act: -0.1700

Data Index: 669690 (C4 (Web Text))

Max Activating Token Index: 442

Text #7

Max Range: 3.5188. Min Range: -3.5188

Max Act: 3.4248. Min Act: -0.1700

Data Index: 956027 (C4 (Web Text))

Max Activating Token Index: 925

Text #8

Max Range: 3.5188. Min Range: -3.5188

Max Act: 3.4248. Min Act: -0.1700

Data Index: 1038882 (C4 (Web Text))

Max Activating Token Index: 232

Text #9

Max Range: 3.5188. Min Range: -3.5188

Max Act: 3.4248. Min Act: -0.1700

Data Index: 1044463 (C4 (Web Text))

Max Activating Token Index: 30

Text #10

Max Range: 3.5188. Min Range: -3.5188

Max Act: 3.4248. Min Act: -0.1700

Data Index: 1089666 (C4 (Web Text))

Max Activating Token Index: 418

Text #11

Max Range: 3.5188. Min Range: -3.5188

Max Act: 3.4248. Min Act: -0.1700

Data Index: 67264 (C4 (Web Text))

Max Activating Token Index: 292

Text #12

Max Range: 3.5188. Min Range: -3.5188

Max Act: 3.3934. Min Act: -0.1700

Data Index: 121821 (C4 (Web Text))

Max Activating Token Index: 781

Text #13

Max Range: 3.5188. Min Range: -3.5188

Max Act: 3.3934. Min Act: -0.1700

Data Index: 758238 (C4 (Web Text))

Max Activating Token Index: 985

Text #14

Max Range: 3.5188. Min Range: -3.5188

Max Act: 3.3934. Min Act: -0.1700

Data Index: 786392 (C4 (Web Text))

Max Activating Token Index: 407

Text #15

Max Range: 3.5188. Min Range: -3.5188

Max Act: 3.3934. Min Act: -0.1700

Data Index: 685066 (C4 (Web Text))

Max Activating Token Index: 135

Text #16

Max Range: 3.5188. Min Range: -3.5188

Max Act: 3.3934. Min Act: -0.1700

Data Index: 180314 (C4 (Web Text))

Max Activating Token Index: 36

Text #17

Max Range: 3.5188. Min Range: -3.5188

Max Act: 3.3777. Min Act: -0.1700

Data Index: 191979 (C4 (Web Text))

Max Activating Token Index: 745

Text #18

Max Range: 3.5188. Min Range: -3.5188

Max Act: 3.4248. Min Act: -0.1700

Data Index: 1261208 (C4 (Web Text))

Max Activating Token Index: 719

Text #19

Max Range: 3.5188. Min Range: -3.5188

Max Act: 3.3934. Min Act: -0.1700

Data Index: 583055 (C4 (Web Text))

Max Activating Token Index: 562