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

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

Neuron 1740 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: 4.1948. Min Range: -4.1948

Max Act: 4.1948. Min Act: -0.1700

Data Index: 132591 (C4 (Web Text))

Max Activating Token Index: 195

Text #1

Max Range: 4.1948. Min Range: -4.1948

Max Act: 4.1948. Min Act: -0.1700

Data Index: 586332 (C4 (Web Text))

Max Activating Token Index: 784

Text #2

Max Range: 4.1948. Min Range: -4.1948

Max Act: 4.1322. Min Act: -0.1700

Data Index: 211707 (C4 (Web Text))

Max Activating Token Index: 831

Text #3

Max Range: 4.1948. Min Range: -4.1948

Max Act: 4.0384. Min Act: -0.1700

Data Index: 824133 (C4 (Web Text))

Max Activating Token Index: 355

Text #4

Max Range: 4.1948. Min Range: -4.1948

Max Act: 3.9759. Min Act: -0.1700

Data Index: 1019387 (C4 (Web Text))

Max Activating Token Index: 307

Text #5

Max Range: 4.1948. Min Range: -4.1948

Max Act: 4.0228. Min Act: -0.1700

Data Index: 291089 (C4 (Web Text))

Max Activating Token Index: 315

Text #6

Max Range: 4.1948. Min Range: -4.1948

Max Act: 3.9916. Min Act: -0.1700

Data Index: 206184 (C4 (Web Text))

Max Activating Token Index: 763

Text #7

Max Range: 4.1948. Min Range: -4.1948

Max Act: 3.9603. Min Act: -0.1700

Data Index: 1050895 (C4 (Web Text))

Max Activating Token Index: 682

Text #8

Max Range: 4.1948. Min Range: -4.1948

Max Act: 3.9916. Min Act: -0.1700

Data Index: 102189 (C4 (Web Text))

Max Activating Token Index: 232

Text #9

Max Range: 4.1948. Min Range: -4.1948

Max Act: 3.9447. Min Act: -0.1700

Data Index: 448869 (C4 (Web Text))

Max Activating Token Index: 739

Text #10

Max Range: 4.1948. Min Range: -4.1948

Max Act: 3.9916. Min Act: -0.1700

Data Index: 951965 (C4 (Web Text))

Max Activating Token Index: 267

Text #11

Max Range: 4.1948. Min Range: -4.1948

Max Act: 3.9134. Min Act: -0.1700

Data Index: 330374 (C4 (Web Text))

Max Activating Token Index: 594

Text #12

Max Range: 4.1948. Min Range: -4.1948

Max Act: 3.9916. Min Act: -0.1700

Data Index: 1257108 (C4 (Web Text))

Max Activating Token Index: 757

Text #13

Max Range: 4.1948. Min Range: -4.1948

Max Act: 3.9916. Min Act: -0.1700

Data Index: 1103958 (C4 (Web Text))

Max Activating Token Index: 373

Text #14

Max Range: 4.1948. Min Range: -4.1948

Max Act: 3.9447. Min Act: -0.1700

Data Index: 527327 (C4 (Web Text))

Max Activating Token Index: 803

Text #15

Max Range: 4.1948. Min Range: -4.1948

Max Act: 3.9916. Min Act: -0.1700

Data Index: 1215601 (C4 (Web Text))

Max Activating Token Index: 618

Text #16

Max Range: 4.1948. Min Range: -4.1948

Max Act: 3.8821. Min Act: -0.1700

Data Index: 1133485 (C4 (Web Text))

Max Activating Token Index: 547

Text #17

Max Range: 4.1948. Min Range: -4.1948

Max Act: 3.9290. Min Act: -0.1700

Data Index: 1087389 (C4 (Web Text))

Max Activating Token Index: 772

Text #18

Max Range: 4.1948. Min Range: -4.1948

Max Act: 3.9290. Min Act: -0.1700

Data Index: 541152 (C4 (Web Text))

Max Activating Token Index: 532

Text #19

Max Range: 4.1948. Min Range: -4.1948

Max Act: 3.8665. Min Act: -0.1700

Data Index: 328071 (C4 (Web Text))

Max Activating Token Index: 446