Model: GELU Model: 2 Layers, 2048 Neurons per Layer

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

Neuron 1818 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-2l')

Text #0

Max Range: 3.5467. Min Range: -3.5467

Max Act: 3.5467. Min Act: -0.1700

Data Index: 984318 (C4 (Web Text))

Max Activating Token Index: 998

Text #1

Max Range: 3.5467. Min Range: -3.5467

Max Act: 3.5467. Min Act: -0.1700

Data Index: 963204 (C4 (Web Text))

Max Activating Token Index: 561

Text #2

Max Range: 3.5467. Min Range: -3.5467

Max Act: 3.5467. Min Act: -0.1700

Data Index: 1149118 (C4 (Web Text))

Max Activating Token Index: 221

Text #3

Max Range: 3.5467. Min Range: -3.5467

Max Act: 3.4214. Min Act: -0.1700

Data Index: 1228328 (C4 (Web Text))

Max Activating Token Index: 245

Text #4

Max Range: 3.5467. Min Range: -3.5467

Max Act: 3.3586. Min Act: -0.1700

Data Index: 252547 (C4 (Web Text))

Max Activating Token Index: 155

Text #5

Max Range: 3.5467. Min Range: -3.5467

Max Act: 3.3272. Min Act: -0.1700

Data Index: 1019301 (C4 (Web Text))

Max Activating Token Index: 401

Text #6

Max Range: 3.5467. Min Range: -3.5467

Max Act: 3.3900. Min Act: -0.1700

Data Index: 396052 (C4 (Web Text))

Max Activating Token Index: 32

Text #7

Max Range: 3.5467. Min Range: -3.5467

Max Act: 3.3586. Min Act: -0.1700

Data Index: 1232274 (C4 (Web Text))

Max Activating Token Index: 173

Text #8

Max Range: 3.5467. Min Range: -3.5467

Max Act: 3.3586. Min Act: -0.1700

Data Index: 847306 (C4 (Web Text))

Max Activating Token Index: 1002

Text #9

Max Range: 3.5467. Min Range: -3.5467

Max Act: 3.3272. Min Act: -0.1700

Data Index: 1644367 (Python Code)

Max Activating Token Index: 352

Text #10

Max Range: 3.5467. Min Range: -3.5467

Max Act: 3.3586. Min Act: -0.1700

Data Index: 760162 (C4 (Web Text))

Max Activating Token Index: 580

Text #11

Max Range: 3.5467. Min Range: -3.5467

Max Act: 3.3272. Min Act: -0.1700

Data Index: 143546 (C4 (Web Text))

Max Activating Token Index: 1020

Text #12

Max Range: 3.5467. Min Range: -3.5467

Max Act: 3.2958. Min Act: -0.1700

Data Index: 288725 (C4 (Web Text))

Max Activating Token Index: 274

Text #13

Max Range: 3.5467. Min Range: -3.5467

Max Act: 3.2644. Min Act: -0.1700

Data Index: 854654 (C4 (Web Text))

Max Activating Token Index: 136

Text #14

Max Range: 3.5467. Min Range: -3.5467

Max Act: 3.2958. Min Act: -0.1700

Data Index: 1203635 (C4 (Web Text))

Max Activating Token Index: 409

Text #15

Max Range: 3.5467. Min Range: -3.5467

Max Act: 3.2330. Min Act: -0.1700

Data Index: 346369 (C4 (Web Text))

Max Activating Token Index: 950

Text #16

Max Range: 3.5467. Min Range: -3.5467

Max Act: 3.3272. Min Act: -0.1700

Data Index: 897252 (C4 (Web Text))

Max Activating Token Index: 431

Text #17

Max Range: 3.5467. Min Range: -3.5467

Max Act: 3.2644. Min Act: -0.1700

Data Index: 90738 (C4 (Web Text))

Max Activating Token Index: 111

Text #18

Max Range: 3.5467. Min Range: -3.5467

Max Act: 3.2644. Min Act: -0.1700

Data Index: 1061824 (C4 (Web Text))

Max Activating Token Index: 253

Text #19

Max Range: 3.5467. Min Range: -3.5467

Max Act: 3.2958. Min Act: -0.1700

Data Index: 253275 (C4 (Web Text))

Max Activating Token Index: 619