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

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

Neuron 1100 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: 5.1802. Min Range: -5.1802

Max Act: 5.1802. Min Act: -0.1700

Data Index: 1062429 (C4 (Web Text))

Max Activating Token Index: 968

Text #1

Max Range: 5.1802. Min Range: -5.1802

Max Act: 4.9927. Min Act: -0.1700

Data Index: 76025 (C4 (Web Text))

Max Activating Token Index: 279

Text #2

Max Range: 5.1802. Min Range: -5.1802

Max Act: 4.8989. Min Act: -0.1700

Data Index: 204414 (C4 (Web Text))

Max Activating Token Index: 299

Text #3

Max Range: 5.1802. Min Range: -5.1802

Max Act: 4.8989. Min Act: -0.1700

Data Index: 74540 (C4 (Web Text))

Max Activating Token Index: 174

Text #4

Max Range: 5.1802. Min Range: -5.1802

Max Act: 4.8364. Min Act: -0.1700

Data Index: 914185 (C4 (Web Text))

Max Activating Token Index: 234

Text #5

Max Range: 5.1802. Min Range: -5.1802

Max Act: 4.8052. Min Act: -0.1700

Data Index: 340567 (C4 (Web Text))

Max Activating Token Index: 406

Text #6

Max Range: 5.1802. Min Range: -5.1802

Max Act: 4.8364. Min Act: -0.1700

Data Index: 712145 (C4 (Web Text))

Max Activating Token Index: 306

Text #7

Max Range: 5.1802. Min Range: -5.1802

Max Act: 4.7739. Min Act: -0.1700

Data Index: 752444 (C4 (Web Text))

Max Activating Token Index: 159

Text #8

Max Range: 5.1802. Min Range: -5.1802

Max Act: 4.7427. Min Act: -0.1700

Data Index: 1001051 (C4 (Web Text))

Max Activating Token Index: 1012

Text #9

Max Range: 5.1802. Min Range: -5.1802

Max Act: 4.8052. Min Act: -0.1700

Data Index: 1137159 (C4 (Web Text))

Max Activating Token Index: 814

Text #10

Max Range: 5.1802. Min Range: -5.1802

Max Act: 4.7114. Min Act: -0.1700

Data Index: 158415 (C4 (Web Text))

Max Activating Token Index: 220

Text #11

Max Range: 5.1802. Min Range: -5.1802

Max Act: 4.6802. Min Act: -0.1700

Data Index: 230675 (C4 (Web Text))

Max Activating Token Index: 114

Text #12

Max Range: 5.1802. Min Range: -5.1802

Max Act: 4.7427. Min Act: -0.1700

Data Index: 571107 (C4 (Web Text))

Max Activating Token Index: 120

Text #13

Max Range: 5.1802. Min Range: -5.1802

Max Act: 4.7114. Min Act: -0.1700

Data Index: 175586 (C4 (Web Text))

Max Activating Token Index: 846

Text #14

Max Range: 5.1802. Min Range: -5.1802

Max Act: 4.7427. Min Act: -0.1700

Data Index: 108508 (C4 (Web Text))

Max Activating Token Index: 510

Text #15

Max Range: 5.1802. Min Range: -5.1802

Max Act: 4.7114. Min Act: -0.1700

Data Index: 1275992 (C4 (Web Text))

Max Activating Token Index: 507

Text #16

Max Range: 5.1802. Min Range: -5.1802

Max Act: 4.7427. Min Act: -0.1700

Data Index: 138765 (C4 (Web Text))

Max Activating Token Index: 220

Text #17

Max Range: 5.1802. Min Range: -5.1802

Max Act: 4.6802. Min Act: -0.1700

Data Index: 512405 (C4 (Web Text))

Max Activating Token Index: 388

Text #18

Max Range: 5.1802. Min Range: -5.1802

Max Act: 4.6802. Min Act: -0.1700

Data Index: 793526 (C4 (Web Text))

Max Activating Token Index: 733

Text #19

Max Range: 5.1802. Min Range: -5.1802

Max Act: 4.6802. Min Act: -0.1700

Data Index: 1174082 (C4 (Web Text))

Max Activating Token Index: 654