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

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

Neuron 1553 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.1411. Min Range: -3.1411

Max Act: 3.1411. Min Act: -0.1700

Data Index: 649531 (C4 (Web Text))

Max Activating Token Index: 408

Text #1

Max Range: 3.1411. Min Range: -3.1411

Max Act: 3.1253. Min Act: -0.1700

Data Index: 826488 (C4 (Web Text))

Max Activating Token Index: 962

Text #2

Max Range: 3.1411. Min Range: -3.1411

Max Act: 3.1096. Min Act: -0.1700

Data Index: 296148 (C4 (Web Text))

Max Activating Token Index: 385

Text #3

Max Range: 3.1411. Min Range: -3.1411

Max Act: 3.1096. Min Act: -0.1700

Data Index: 959746 (C4 (Web Text))

Max Activating Token Index: 6

Text #4

Max Range: 3.1411. Min Range: -3.1411

Max Act: 3.0938. Min Act: -0.1700

Data Index: 781853 (C4 (Web Text))

Max Activating Token Index: 395

Text #5

Max Range: 3.1411. Min Range: -3.1411

Max Act: 3.0622. Min Act: -0.1700

Data Index: 646679 (C4 (Web Text))

Max Activating Token Index: 787

Text #6

Max Range: 3.1411. Min Range: -3.1411

Max Act: 3.0465. Min Act: -0.1700

Data Index: 127182 (C4 (Web Text))

Max Activating Token Index: 462

Text #7

Max Range: 3.1411. Min Range: -3.1411

Max Act: 3.0465. Min Act: -0.1700

Data Index: 396965 (C4 (Web Text))

Max Activating Token Index: 241

Text #8

Max Range: 3.1411. Min Range: -3.1411

Max Act: 3.0465. Min Act: -0.1700

Data Index: 1341489 (C4 (Web Text))

Max Activating Token Index: 463

Text #9

Max Range: 3.1411. Min Range: -3.1411

Max Act: 3.0149. Min Act: -0.1700

Data Index: 1052943 (C4 (Web Text))

Max Activating Token Index: 478

Text #10

Max Range: 3.1411. Min Range: -3.1411

Max Act: 3.0465. Min Act: -0.1700

Data Index: 1098179 (C4 (Web Text))

Max Activating Token Index: 870

Text #11

Max Range: 3.1411. Min Range: -3.1411

Max Act: 3.0307. Min Act: -0.1700

Data Index: 74077 (C4 (Web Text))

Max Activating Token Index: 288

Text #12

Max Range: 3.1411. Min Range: -3.1411

Max Act: 3.0149. Min Act: -0.1700

Data Index: 1206802 (C4 (Web Text))

Max Activating Token Index: 294

Text #13

Max Range: 3.1411. Min Range: -3.1411

Max Act: 3.0307. Min Act: -0.1700

Data Index: 1090843 (C4 (Web Text))

Max Activating Token Index: 381

Text #14

Max Range: 3.1411. Min Range: -3.1411

Max Act: 3.0307. Min Act: -0.1700

Data Index: 1095359 (C4 (Web Text))

Max Activating Token Index: 889

Text #15

Max Range: 3.1411. Min Range: -3.1411

Max Act: 3.0149. Min Act: -0.1700

Data Index: 699353 (C4 (Web Text))

Max Activating Token Index: 351

Text #16

Max Range: 3.1411. Min Range: -3.1411

Max Act: 3.0307. Min Act: -0.1700

Data Index: 313163 (C4 (Web Text))

Max Activating Token Index: 770

Text #17

Max Range: 3.1411. Min Range: -3.1411

Max Act: 2.9991. Min Act: -0.1700

Data Index: 398776 (C4 (Web Text))

Max Activating Token Index: 249

Text #18

Max Range: 3.1411. Min Range: -3.1411

Max Act: 3.0149. Min Act: -0.1700

Data Index: 262521 (C4 (Web Text))

Max Activating Token Index: 194

Text #19

Max Range: 3.1411. Min Range: -3.1411

Max Act: 2.9991. Min Act: -0.1700

Data Index: 308418 (C4 (Web Text))

Max Activating Token Index: 222