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

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

Neuron 2044 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: 3.4720. Min Range: -3.4720

Max Act: 3.4406. Min Act: -0.1700

Data Index: 604561 (C4 (Web Text))

Max Activating Token Index: 778

Text #1

Max Range: 3.4720. Min Range: -3.4720

Max Act: 3.4720. Min Act: -0.1700

Data Index: 92661 (C4 (Web Text))

Max Activating Token Index: 247

Text #2

Max Range: 3.4720. Min Range: -3.4720

Max Act: 3.4093. Min Act: -0.1700

Data Index: 566063 (C4 (Web Text))

Max Activating Token Index: 591

Text #3

Max Range: 3.4720. Min Range: -3.4720

Max Act: 3.4249. Min Act: -0.1700

Data Index: 1174484 (C4 (Web Text))

Max Activating Token Index: 666

Text #4

Max Range: 3.4720. Min Range: -3.4720

Max Act: 3.3622. Min Act: -0.1700

Data Index: 874431 (C4 (Web Text))

Max Activating Token Index: 359

Text #5

Max Range: 3.4720. Min Range: -3.4720

Max Act: 3.3308. Min Act: -0.1700

Data Index: 734508 (C4 (Web Text))

Max Activating Token Index: 1018

Text #6

Max Range: 3.4720. Min Range: -3.4720

Max Act: 3.3308. Min Act: -0.1700

Data Index: 858865 (C4 (Web Text))

Max Activating Token Index: 74

Text #7

Max Range: 3.4720. Min Range: -3.4720

Max Act: 3.3151. Min Act: -0.1700

Data Index: 173132 (C4 (Web Text))

Max Activating Token Index: 839

Text #8

Max Range: 3.4720. Min Range: -3.4720

Max Act: 3.3308. Min Act: -0.1700

Data Index: 734743 (C4 (Web Text))

Max Activating Token Index: 272

Text #9

Max Range: 3.4720. Min Range: -3.4720

Max Act: 3.2523. Min Act: -0.1700

Data Index: 895712 (C4 (Web Text))

Max Activating Token Index: 707

Text #10

Max Range: 3.4720. Min Range: -3.4720

Max Act: 3.3465. Min Act: -0.1700

Data Index: 1323919 (C4 (Web Text))

Max Activating Token Index: 641

Text #11

Max Range: 3.4720. Min Range: -3.4720

Max Act: 3.3151. Min Act: -0.1700

Data Index: 994197 (C4 (Web Text))

Max Activating Token Index: 166

Text #12

Max Range: 3.4720. Min Range: -3.4720

Max Act: 3.2837. Min Act: -0.1700

Data Index: 1197999 (C4 (Web Text))

Max Activating Token Index: 318

Text #13

Max Range: 3.4720. Min Range: -3.4720

Max Act: 3.2994. Min Act: -0.1700

Data Index: 1288479 (C4 (Web Text))

Max Activating Token Index: 317

Text #14

Max Range: 3.4720. Min Range: -3.4720

Max Act: 3.2523. Min Act: -0.1700

Data Index: 12648 (C4 (Web Text))

Max Activating Token Index: 454

Text #15

Max Range: 3.4720. Min Range: -3.4720

Max Act: 3.2680. Min Act: -0.1700

Data Index: 1093921 (C4 (Web Text))

Max Activating Token Index: 850

Text #16

Max Range: 3.4720. Min Range: -3.4720

Max Act: 3.2523. Min Act: -0.1700

Data Index: 1003432 (C4 (Web Text))

Max Activating Token Index: 129

Text #17

Max Range: 3.4720. Min Range: -3.4720

Max Act: 3.2680. Min Act: -0.1700

Data Index: 141587 (C4 (Web Text))

Max Activating Token Index: 15

Text #18

Max Range: 3.4720. Min Range: -3.4720

Max Act: 3.2680. Min Act: -0.1700

Data Index: 478195 (C4 (Web Text))

Max Activating Token Index: 339

Text #19

Max Range: 3.4720. Min Range: -3.4720

Max Act: 3.2837. Min Act: -0.1700

Data Index: 813767 (C4 (Web Text))

Max Activating Token Index: 692