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

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

Neuron 1182 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.9026. Min Range: -5.9026

Max Act: 5.9026. Min Act: -0.1700

Data Index: 364568 (C4 (Web Text))

Max Activating Token Index: 720

Text #1

Max Range: 5.9026. Min Range: -5.9026

Max Act: 5.8089. Min Act: -0.1700

Data Index: 358541 (C4 (Web Text))

Max Activating Token Index: 395

Text #2

Max Range: 5.9026. Min Range: -5.9026

Max Act: 5.7932. Min Act: -0.1700

Data Index: 587388 (C4 (Web Text))

Max Activating Token Index: 761

Text #3

Max Range: 5.9026. Min Range: -5.9026

Max Act: 5.7464. Min Act: -0.1700

Data Index: 721266 (C4 (Web Text))

Max Activating Token Index: 761

Text #4

Max Range: 5.9026. Min Range: -5.9026

Max Act: 5.6995. Min Act: -0.1700

Data Index: 603147 (C4 (Web Text))

Max Activating Token Index: 738

Text #5

Max Range: 5.9026. Min Range: -5.9026

Max Act: 5.6526. Min Act: -0.1700

Data Index: 1563406 (Python Code)

Max Activating Token Index: 987

Text #6

Max Range: 5.9026. Min Range: -5.9026

Max Act: 5.5120. Min Act: -0.1699

Data Index: 249752 (C4 (Web Text))

Max Activating Token Index: 907

Text #7

Max Range: 5.9026. Min Range: -5.9026

Max Act: 5.7151. Min Act: -0.1700

Data Index: 127942 (C4 (Web Text))

Max Activating Token Index: 217

Text #8

Max Range: 5.9026. Min Range: -5.9026

Max Act: 5.6214. Min Act: -0.1700

Data Index: 674307 (C4 (Web Text))

Max Activating Token Index: 756

Text #9

Max Range: 5.9026. Min Range: -5.9026

Max Act: 5.6370. Min Act: -0.1700

Data Index: 846192 (C4 (Web Text))

Max Activating Token Index: 1016

Text #10

Max Range: 5.9026. Min Range: -5.9026

Max Act: 5.6682. Min Act: -0.1700

Data Index: 858466 (C4 (Web Text))

Max Activating Token Index: 628

Text #11

Max Range: 5.9026. Min Range: -5.9026

Max Act: 5.5901. Min Act: -0.1700

Data Index: 783012 (C4 (Web Text))

Max Activating Token Index: 731

Text #12

Max Range: 5.9026. Min Range: -5.9026

Max Act: 5.6682. Min Act: -0.1700

Data Index: 1086926 (C4 (Web Text))

Max Activating Token Index: 464

Text #13

Max Range: 5.9026. Min Range: -5.9026

Max Act: 5.6370. Min Act: -0.1700

Data Index: 527767 (C4 (Web Text))

Max Activating Token Index: 234

Text #14

Max Range: 5.9026. Min Range: -5.9026

Max Act: 5.6214. Min Act: -0.1700

Data Index: 472764 (C4 (Web Text))

Max Activating Token Index: 412

Text #15

Max Range: 5.9026. Min Range: -5.9026

Max Act: 5.5901. Min Act: -0.1699

Data Index: 842286 (C4 (Web Text))

Max Activating Token Index: 286

Text #16

Max Range: 5.9026. Min Range: -5.9026

Max Act: 5.5432. Min Act: -0.1700

Data Index: 373625 (C4 (Web Text))

Max Activating Token Index: 353

Text #17

Max Range: 5.9026. Min Range: -5.9026

Max Act: 5.5276. Min Act: -0.1700

Data Index: 791666 (C4 (Web Text))

Max Activating Token Index: 821

Text #18

Max Range: 5.9026. Min Range: -5.9026

Max Act: 5.5589. Min Act: -0.1700

Data Index: 1240995 (C4 (Web Text))

Max Activating Token Index: 327

Text #19

Max Range: 5.9026. Min Range: -5.9026

Max Act: 5.5745. Min Act: -0.1700

Data Index: 1314708 (C4 (Web Text))

Max Activating Token Index: 408