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

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

Neuron 72 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: 3.3910. Min Range: -3.3910

Max Act: 3.3910. Min Act: -0.1700

Data Index: 550084 (C4 (Web Text))

Max Activating Token Index: 34

Text #1

Max Range: 3.3910. Min Range: -3.3910

Max Act: 3.3439. Min Act: -0.1700

Data Index: 388752 (C4 (Web Text))

Max Activating Token Index: 67

Text #2

Max Range: 3.3910. Min Range: -3.3910

Max Act: 3.3439. Min Act: -0.1700

Data Index: 667861 (C4 (Web Text))

Max Activating Token Index: 50

Text #3

Max Range: 3.3910. Min Range: -3.3910

Max Act: 3.2968. Min Act: -0.1700

Data Index: 75313 (C4 (Web Text))

Max Activating Token Index: 741

Text #4

Max Range: 3.3910. Min Range: -3.3910

Max Act: 3.2340. Min Act: -0.1700

Data Index: 180001 (C4 (Web Text))

Max Activating Token Index: 195

Text #5

Max Range: 3.3910. Min Range: -3.3910

Max Act: 3.1868. Min Act: -0.1700

Data Index: 263892 (C4 (Web Text))

Max Activating Token Index: 162

Text #6

Max Range: 3.3910. Min Range: -3.3910

Max Act: 3.2025. Min Act: -0.1700

Data Index: 622359 (C4 (Web Text))

Max Activating Token Index: 509

Text #7

Max Range: 3.3910. Min Range: -3.3910

Max Act: 3.2025. Min Act: -0.1700

Data Index: 682418 (C4 (Web Text))

Max Activating Token Index: 950

Text #8

Max Range: 3.3910. Min Range: -3.3910

Max Act: 3.1553. Min Act: -0.1700

Data Index: 138199 (C4 (Web Text))

Max Activating Token Index: 716

Text #9

Max Range: 3.3910. Min Range: -3.3910

Max Act: 3.1710. Min Act: -0.1700

Data Index: 341588 (C4 (Web Text))

Max Activating Token Index: 374

Text #10

Max Range: 3.3910. Min Range: -3.3910

Max Act: 3.1395. Min Act: -0.1700

Data Index: 527452 (C4 (Web Text))

Max Activating Token Index: 1023

Text #11

Max Range: 3.3910. Min Range: -3.3910

Max Act: 3.1395. Min Act: -0.1700

Data Index: 1319004 (C4 (Web Text))

Max Activating Token Index: 287

Text #12

Max Range: 3.3910. Min Range: -3.3910

Max Act: 3.0922. Min Act: -0.1700

Data Index: 1014677 (C4 (Web Text))

Max Activating Token Index: 783

Text #13

Max Range: 3.3910. Min Range: -3.3910

Max Act: 3.1553. Min Act: -0.1700

Data Index: 639474 (C4 (Web Text))

Max Activating Token Index: 541

Text #14

Max Range: 3.3910. Min Range: -3.3910

Max Act: 3.1395. Min Act: -0.1700

Data Index: 1217915 (C4 (Web Text))

Max Activating Token Index: 243

Text #15

Max Range: 3.3910. Min Range: -3.3910

Max Act: 3.1238. Min Act: -0.1700

Data Index: 431063 (C4 (Web Text))

Max Activating Token Index: 404

Text #16

Max Range: 3.3910. Min Range: -3.3910

Max Act: 3.1553. Min Act: -0.1700

Data Index: 872431 (C4 (Web Text))

Max Activating Token Index: 844

Text #17

Max Range: 3.3910. Min Range: -3.3910

Max Act: 3.1238. Min Act: -0.1700

Data Index: 10509 (C4 (Web Text))

Max Activating Token Index: 276

Text #18

Max Range: 3.3910. Min Range: -3.3910

Max Act: 3.1080. Min Act: -0.1700

Data Index: 96163 (C4 (Web Text))

Max Activating Token Index: 643

Text #19

Max Range: 3.3910. Min Range: -3.3910

Max Act: 3.1080. Min Act: -0.1700

Data Index: 1053742 (C4 (Web Text))

Max Activating Token Index: 171