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

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

Neuron 391 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 6.0403. Min Range: -6.0403

Max Act: 6.0403. Min Act: -0.1700

Data Index: 1344082 (C4 (Web Text))

Max Activating Token Index: 730

Text #1

Max Range: 6.0403. Min Range: -6.0403

Max Act: 5.8371. Min Act: -0.1700

Data Index: 195112 (C4 (Web Text))

Max Activating Token Index: 360

Text #2

Max Range: 6.0403. Min Range: -6.0403

Max Act: 5.7434. Min Act: -0.1700

Data Index: 992872 (C4 (Web Text))

Max Activating Token Index: 547

Text #3

Max Range: 6.0403. Min Range: -6.0403

Max Act: 5.7434. Min Act: -0.1700

Data Index: 1232110 (C4 (Web Text))

Max Activating Token Index: 425

Text #4

Max Range: 6.0403. Min Range: -6.0403

Max Act: 5.7746. Min Act: -0.1700

Data Index: 1266447 (C4 (Web Text))

Max Activating Token Index: 301

Text #5

Max Range: 6.0403. Min Range: -6.0403

Max Act: 5.6965. Min Act: -0.1700

Data Index: 311544 (C4 (Web Text))

Max Activating Token Index: 730

Text #6

Max Range: 6.0403. Min Range: -6.0403

Max Act: 5.7278. Min Act: -0.1700

Data Index: 183881 (C4 (Web Text))

Max Activating Token Index: 128

Text #7

Max Range: 6.0403. Min Range: -6.0403

Max Act: 5.6965. Min Act: -0.1700

Data Index: 83315 (C4 (Web Text))

Max Activating Token Index: 315

Text #8

Max Range: 6.0403. Min Range: -6.0403

Max Act: 5.6653. Min Act: -0.1700

Data Index: 489198 (C4 (Web Text))

Max Activating Token Index: 167

Text #9

Max Range: 6.0403. Min Range: -6.0403

Max Act: 5.5246. Min Act: -0.1700

Data Index: 992789 (C4 (Web Text))

Max Activating Token Index: 372

Text #10

Max Range: 6.0403. Min Range: -6.0403

Max Act: 5.5403. Min Act: -0.1700

Data Index: 664973 (C4 (Web Text))

Max Activating Token Index: 358

Text #11

Max Range: 6.0403. Min Range: -6.0403

Max Act: 5.6496. Min Act: -0.1700

Data Index: 314035 (C4 (Web Text))

Max Activating Token Index: 89

Text #12

Max Range: 6.0403. Min Range: -6.0403

Max Act: 5.6340. Min Act: -0.1700

Data Index: 732373 (C4 (Web Text))

Max Activating Token Index: 939

Text #13

Max Range: 6.0403. Min Range: -6.0403

Max Act: 5.5403. Min Act: -0.1700

Data Index: 442897 (C4 (Web Text))

Max Activating Token Index: 248

Text #14

Max Range: 6.0403. Min Range: -6.0403

Max Act: 5.5871. Min Act: -0.1700

Data Index: 410563 (C4 (Web Text))

Max Activating Token Index: 69

Text #15

Max Range: 6.0403. Min Range: -6.0403

Max Act: 5.6965. Min Act: -0.1700

Data Index: 570228 (C4 (Web Text))

Max Activating Token Index: 222

Text #16

Max Range: 6.0403. Min Range: -6.0403

Max Act: 5.4778. Min Act: -0.1700

Data Index: 34831 (C4 (Web Text))

Max Activating Token Index: 182

Text #17

Max Range: 6.0403. Min Range: -6.0403

Max Act: 5.4153. Min Act: -0.1700

Data Index: 1121566 (C4 (Web Text))

Max Activating Token Index: 180

Text #18

Max Range: 6.0403. Min Range: -6.0403

Max Act: 5.4309. Min Act: -0.1700

Data Index: 1249499 (C4 (Web Text))

Max Activating Token Index: 381

Text #19

Max Range: 6.0403. Min Range: -6.0403

Max Act: 5.4778. Min Act: -0.1700

Data Index: 1541567 (Python Code)

Max Activating Token Index: 661