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

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

Neuron 1480 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.3028. Min Range: -3.3028

Max Act: 3.3028. Min Act: -0.1700

Data Index: 1164187 (C4 (Web Text))

Max Activating Token Index: 94

Text #1

Max Range: 3.3028. Min Range: -3.3028

Max Act: 3.0983. Min Act: -0.1700

Data Index: 103924 (C4 (Web Text))

Max Activating Token Index: 765

Text #2

Max Range: 3.3028. Min Range: -3.3028

Max Act: 3.1140. Min Act: -0.1700

Data Index: 532114 (C4 (Web Text))

Max Activating Token Index: 738

Text #3

Max Range: 3.3028. Min Range: -3.3028

Max Act: 3.0667. Min Act: -0.1700

Data Index: 392651 (C4 (Web Text))

Max Activating Token Index: 966

Text #4

Max Range: 3.3028. Min Range: -3.3028

Max Act: 3.0667. Min Act: -0.1700

Data Index: 52651 (C4 (Web Text))

Max Activating Token Index: 374

Text #5

Max Range: 3.3028. Min Range: -3.3028

Max Act: 3.1298. Min Act: -0.1700

Data Index: 368676 (C4 (Web Text))

Max Activating Token Index: 708

Text #6

Max Range: 3.3028. Min Range: -3.3028

Max Act: 3.0193. Min Act: -0.1700

Data Index: 943149 (C4 (Web Text))

Max Activating Token Index: 401

Text #7

Max Range: 3.3028. Min Range: -3.3028

Max Act: 3.0509. Min Act: -0.1700

Data Index: 1203792 (C4 (Web Text))

Max Activating Token Index: 159

Text #8

Max Range: 3.3028. Min Range: -3.3028

Max Act: 3.0667. Min Act: -0.1700

Data Index: 261012 (C4 (Web Text))

Max Activating Token Index: 830

Text #9

Max Range: 3.3028. Min Range: -3.3028

Max Act: 3.0667. Min Act: -0.1700

Data Index: 379442 (C4 (Web Text))

Max Activating Token Index: 265

Text #10

Max Range: 3.3028. Min Range: -3.3028

Max Act: 3.0193. Min Act: -0.1700

Data Index: 31733 (C4 (Web Text))

Max Activating Token Index: 272

Text #11

Max Range: 3.3028. Min Range: -3.3028

Max Act: 3.0193. Min Act: -0.1700

Data Index: 577621 (C4 (Web Text))

Max Activating Token Index: 590

Text #12

Max Range: 3.3028. Min Range: -3.3028

Max Act: 2.9561. Min Act: -0.1700

Data Index: 1019541 (C4 (Web Text))

Max Activating Token Index: 492

Text #13

Max Range: 3.3028. Min Range: -3.3028

Max Act: 3.0351. Min Act: -0.1700

Data Index: 1078380 (C4 (Web Text))

Max Activating Token Index: 206

Text #14

Max Range: 3.3028. Min Range: -3.3028

Max Act: 2.9877. Min Act: -0.1700

Data Index: 599735 (C4 (Web Text))

Max Activating Token Index: 678

Text #15

Max Range: 3.3028. Min Range: -3.3028

Max Act: 2.9877. Min Act: -0.1700

Data Index: 302885 (C4 (Web Text))

Max Activating Token Index: 90

Text #16

Max Range: 3.3028. Min Range: -3.3028

Max Act: 2.9561. Min Act: -0.1700

Data Index: 1210246 (C4 (Web Text))

Max Activating Token Index: 42

Text #17

Max Range: 3.3028. Min Range: -3.3028

Max Act: 2.9719. Min Act: -0.1700

Data Index: 492967 (C4 (Web Text))

Max Activating Token Index: 296

Text #18

Max Range: 3.3028. Min Range: -3.3028

Max Act: 2.9561. Min Act: -0.1700

Data Index: 190919 (C4 (Web Text))

Max Activating Token Index: 390

Text #19

Max Range: 3.3028. Min Range: -3.3028

Max Act: 2.9719. Min Act: -0.1700

Data Index: 841019 (C4 (Web Text))

Max Activating Token Index: 603