Model: GELU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 1813 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')

Text #0

Max Range: 3.4692. Min Range: -3.4692

Max Act: 3.4535. Min Act: -0.1700

Data Index: 840108 (C4 (Web Text))

Max Activating Token Index: 1018

Text #1

Max Range: 3.4692. Min Range: -3.4692

Max Act: 3.4692. Min Act: -0.1700

Data Index: 466833 (C4 (Web Text))

Max Activating Token Index: 333

Text #2

Max Range: 3.4692. Min Range: -3.4692

Max Act: 3.3751. Min Act: -0.1700

Data Index: 568756 (C4 (Web Text))

Max Activating Token Index: 293

Text #3

Max Range: 3.4692. Min Range: -3.4692

Max Act: 3.3280. Min Act: -0.1700

Data Index: 655255 (C4 (Web Text))

Max Activating Token Index: 812

Text #4

Max Range: 3.4692. Min Range: -3.4692

Max Act: 3.4222. Min Act: -0.1700

Data Index: 205021 (C4 (Web Text))

Max Activating Token Index: 895

Text #5

Max Range: 3.4692. Min Range: -3.4692

Max Act: 3.3123. Min Act: -0.1700

Data Index: 1068361 (C4 (Web Text))

Max Activating Token Index: 650

Text #6

Max Range: 3.4692. Min Range: -3.4692

Max Act: 3.3594. Min Act: -0.1700

Data Index: 1173334 (C4 (Web Text))

Max Activating Token Index: 502

Text #7

Max Range: 3.4692. Min Range: -3.4692

Max Act: 3.3280. Min Act: -0.1700

Data Index: 856427 (C4 (Web Text))

Max Activating Token Index: 696

Text #8

Max Range: 3.4692. Min Range: -3.4692

Max Act: 3.3123. Min Act: -0.1700

Data Index: 304610 (C4 (Web Text))

Max Activating Token Index: 970

Text #9

Max Range: 3.4692. Min Range: -3.4692

Max Act: 3.3908. Min Act: -0.1700

Data Index: 281148 (C4 (Web Text))

Max Activating Token Index: 960

Text #10

Max Range: 3.4692. Min Range: -3.4692

Max Act: 3.3594. Min Act: -0.1700

Data Index: 483331 (C4 (Web Text))

Max Activating Token Index: 756

Text #11

Max Range: 3.4692. Min Range: -3.4692

Max Act: 3.3437. Min Act: -0.1700

Data Index: 306615 (C4 (Web Text))

Max Activating Token Index: 675

Text #12

Max Range: 3.4692. Min Range: -3.4692

Max Act: 3.2652. Min Act: -0.1700

Data Index: 959334 (C4 (Web Text))

Max Activating Token Index: 1019

Text #13

Max Range: 3.4692. Min Range: -3.4692

Max Act: 3.2809. Min Act: -0.1700

Data Index: 1028046 (C4 (Web Text))

Max Activating Token Index: 205

Text #14

Max Range: 3.4692. Min Range: -3.4692

Max Act: 3.2652. Min Act: -0.1700

Data Index: 410557 (C4 (Web Text))

Max Activating Token Index: 703

Text #15

Max Range: 3.4692. Min Range: -3.4692

Max Act: 3.2652. Min Act: -0.1700

Data Index: 951914 (C4 (Web Text))

Max Activating Token Index: 811

Text #16

Max Range: 3.4692. Min Range: -3.4692

Max Act: 3.2809. Min Act: -0.1700

Data Index: 1045585 (C4 (Web Text))

Max Activating Token Index: 682

Text #17

Max Range: 3.4692. Min Range: -3.4692

Max Act: 3.2652. Min Act: -0.1700

Data Index: 541464 (C4 (Web Text))

Max Activating Token Index: 892

Text #18

Max Range: 3.4692. Min Range: -3.4692

Max Act: 3.3123. Min Act: -0.1700

Data Index: 700630 (C4 (Web Text))

Max Activating Token Index: 394

Text #19

Max Range: 3.4692. Min Range: -3.4692

Max Act: 3.2809. Min Act: -0.1700

Data Index: 665286 (C4 (Web Text))

Max Activating Token Index: 946