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

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

Neuron 1916 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.1335. Min Range: -5.1335

Max Act: 5.1335. Min Act: -0.1700

Data Index: 796762 (C4 (Web Text))

Max Activating Token Index: 119

Text #1

Max Range: 5.1335. Min Range: -5.1335

Max Act: 5.0710. Min Act: -0.1700

Data Index: 225716 (C4 (Web Text))

Max Activating Token Index: 571

Text #2

Max Range: 5.1335. Min Range: -5.1335

Max Act: 5.0710. Min Act: -0.1700

Data Index: 150058 (C4 (Web Text))

Max Activating Token Index: 440

Text #3

Max Range: 5.1335. Min Range: -5.1335

Max Act: 5.0397. Min Act: -0.1700

Data Index: 827271 (C4 (Web Text))

Max Activating Token Index: 372

Text #4

Max Range: 5.1335. Min Range: -5.1335

Max Act: 4.9772. Min Act: -0.1700

Data Index: 571378 (C4 (Web Text))

Max Activating Token Index: 814

Text #5

Max Range: 5.1335. Min Range: -5.1335

Max Act: 5.0397. Min Act: -0.1700

Data Index: 1272663 (C4 (Web Text))

Max Activating Token Index: 925

Text #6

Max Range: 5.1335. Min Range: -5.1335

Max Act: 5.0085. Min Act: -0.1700

Data Index: 176237 (C4 (Web Text))

Max Activating Token Index: 474

Text #7

Max Range: 5.1335. Min Range: -5.1335

Max Act: 5.0085. Min Act: -0.1700

Data Index: 959175 (C4 (Web Text))

Max Activating Token Index: 169

Text #8

Max Range: 5.1335. Min Range: -5.1335

Max Act: 4.9460. Min Act: -0.1700

Data Index: 1009569 (C4 (Web Text))

Max Activating Token Index: 502

Text #9

Max Range: 5.1335. Min Range: -5.1335

Max Act: 4.9772. Min Act: -0.1700

Data Index: 196664 (C4 (Web Text))

Max Activating Token Index: 454

Text #10

Max Range: 5.1335. Min Range: -5.1335

Max Act: 4.9460. Min Act: -0.1700

Data Index: 77230 (C4 (Web Text))

Max Activating Token Index: 824

Text #11

Max Range: 5.1335. Min Range: -5.1335

Max Act: 4.9460. Min Act: -0.1700

Data Index: 110423 (C4 (Web Text))

Max Activating Token Index: 101

Text #12

Max Range: 5.1335. Min Range: -5.1335

Max Act: 4.9460. Min Act: -0.1700

Data Index: 315515 (C4 (Web Text))

Max Activating Token Index: 583

Text #13

Max Range: 5.1335. Min Range: -5.1335

Max Act: 4.9147. Min Act: -0.1700

Data Index: 219299 (C4 (Web Text))

Max Activating Token Index: 913

Text #14

Max Range: 5.1335. Min Range: -5.1335

Max Act: 4.9147. Min Act: -0.1700

Data Index: 1132744 (C4 (Web Text))

Max Activating Token Index: 428

Text #15

Max Range: 5.1335. Min Range: -5.1335

Max Act: 4.9460. Min Act: -0.1700

Data Index: 1358711 (C4 (Web Text))

Max Activating Token Index: 831

Text #16

Max Range: 5.1335. Min Range: -5.1335

Max Act: 4.8835. Min Act: -0.1700

Data Index: 1296608 (C4 (Web Text))

Max Activating Token Index: 155

Text #17

Max Range: 5.1335. Min Range: -5.1335

Max Act: 4.9147. Min Act: -0.1700

Data Index: 917252 (C4 (Web Text))

Max Activating Token Index: 760

Text #18

Max Range: 5.1335. Min Range: -5.1335

Max Act: 4.8835. Min Act: -0.1700

Data Index: 9914 (C4 (Web Text))

Max Activating Token Index: 224

Text #19

Max Range: 5.1335. Min Range: -5.1335

Max Act: 4.8835. Min Act: -0.1700

Data Index: 169989 (C4 (Web Text))

Max Activating Token Index: 333