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

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

Neuron 953 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 7.7086. Min Range: -7.7086

Max Act: 7.7086. Min Act: -0.1700

Data Index: 194030 (C4 (Web Text))

Max Activating Token Index: 132

Text #1

Max Range: 7.7086. Min Range: -7.7086

Max Act: 7.5836. Min Act: -0.1700

Data Index: 951783 (C4 (Web Text))

Max Activating Token Index: 15

Text #2

Max Range: 7.7086. Min Range: -7.7086

Max Act: 7.6149. Min Act: -0.1700

Data Index: 303733 (C4 (Web Text))

Max Activating Token Index: 212

Text #3

Max Range: 7.7086. Min Range: -7.7086

Max Act: 7.5524. Min Act: -0.1700

Data Index: 93739 (C4 (Web Text))

Max Activating Token Index: 1023

Text #4

Max Range: 7.7086. Min Range: -7.7086

Max Act: 7.6149. Min Act: -0.1700

Data Index: 561035 (C4 (Web Text))

Max Activating Token Index: 141

Text #5

Max Range: 7.7086. Min Range: -7.7086

Max Act: 7.4274. Min Act: -0.1700

Data Index: 301832 (C4 (Web Text))

Max Activating Token Index: 435

Text #6

Max Range: 7.7086. Min Range: -7.7086

Max Act: 7.4274. Min Act: -0.1700

Data Index: 657965 (C4 (Web Text))

Max Activating Token Index: 140

Text #7

Max Range: 7.7086. Min Range: -7.7086

Max Act: 7.4586. Min Act: -0.1700

Data Index: 29056 (C4 (Web Text))

Max Activating Token Index: 353

Text #8

Max Range: 7.7086. Min Range: -7.7086

Max Act: 7.4586. Min Act: -0.1700

Data Index: 25947 (C4 (Web Text))

Max Activating Token Index: 46

Text #9

Max Range: 7.7086. Min Range: -7.7086

Max Act: 7.4586. Min Act: -0.1700

Data Index: 503436 (C4 (Web Text))

Max Activating Token Index: 803

Text #10

Max Range: 7.7086. Min Range: -7.7086

Max Act: 7.4274. Min Act: -0.1700

Data Index: 1016397 (C4 (Web Text))

Max Activating Token Index: 774

Text #11

Max Range: 7.7086. Min Range: -7.7086

Max Act: 7.4274. Min Act: -0.1700

Data Index: 634008 (C4 (Web Text))

Max Activating Token Index: 544

Text #12

Max Range: 7.7086. Min Range: -7.7086

Max Act: 7.3336. Min Act: -0.1700

Data Index: 691301 (C4 (Web Text))

Max Activating Token Index: 391

Text #13

Max Range: 7.7086. Min Range: -7.7086

Max Act: 7.3024. Min Act: -0.1700

Data Index: 24843 (C4 (Web Text))

Max Activating Token Index: 821

Text #14

Max Range: 7.7086. Min Range: -7.7086

Max Act: 7.3336. Min Act: -0.1700

Data Index: 936264 (C4 (Web Text))

Max Activating Token Index: 482

Text #15

Max Range: 7.7086. Min Range: -7.7086

Max Act: 7.3024. Min Act: -0.1700

Data Index: 462855 (C4 (Web Text))

Max Activating Token Index: 207

Text #16

Max Range: 7.7086. Min Range: -7.7086

Max Act: 7.2399. Min Act: -0.1700

Data Index: 358072 (C4 (Web Text))

Max Activating Token Index: 217

Text #17

Max Range: 7.7086. Min Range: -7.7086

Max Act: 7.2399. Min Act: -0.1700

Data Index: 966178 (C4 (Web Text))

Max Activating Token Index: 376

Text #18

Max Range: 7.7086. Min Range: -7.7086

Max Act: 7.1149. Min Act: -0.1700

Data Index: 1078631 (C4 (Web Text))

Max Activating Token Index: 330

Text #19

Max Range: 7.7086. Min Range: -7.7086

Max Act: 7.2399. Min Act: -0.1700

Data Index: 1103479 (C4 (Web Text))

Max Activating Token Index: 273