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

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

Neuron 1034 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.4320. Min Range: -3.4320

Max Act: 3.4320. Min Act: -0.1700

Data Index: 1632604 (Python Code)

Max Activating Token Index: 617

Text #1

Max Range: 3.4320. Min Range: -3.4320

Max Act: 3.4164. Min Act: -0.1700

Data Index: 1372856 (Python Code)

Max Activating Token Index: 413

Text #2

Max Range: 3.4320. Min Range: -3.4320

Max Act: 3.4164. Min Act: -0.1700

Data Index: 1366459 (Python Code)

Max Activating Token Index: 682

Text #3

Max Range: 3.4320. Min Range: -3.4320

Max Act: 3.3693. Min Act: -0.1700

Data Index: 952207 (C4 (Web Text))

Max Activating Token Index: 688

Text #4

Max Range: 3.4320. Min Range: -3.4320

Max Act: 3.3536. Min Act: -0.1700

Data Index: 1107074 (C4 (Web Text))

Max Activating Token Index: 437

Text #5

Max Range: 3.4320. Min Range: -3.4320

Max Act: 3.3222. Min Act: -0.1700

Data Index: 1408421 (Python Code)

Max Activating Token Index: 237

Text #6

Max Range: 3.4320. Min Range: -3.4320

Max Act: 3.3379. Min Act: -0.1700

Data Index: 1499244 (Python Code)

Max Activating Token Index: 824

Text #7

Max Range: 3.4320. Min Range: -3.4320

Max Act: 3.2751. Min Act: -0.1700

Data Index: 379187 (C4 (Web Text))

Max Activating Token Index: 568

Text #8

Max Range: 3.4320. Min Range: -3.4320

Max Act: 3.2751. Min Act: -0.1700

Data Index: 1059932 (C4 (Web Text))

Max Activating Token Index: 841

Text #9

Max Range: 3.4320. Min Range: -3.4320

Max Act: 3.2908. Min Act: -0.1700

Data Index: 1591791 (Python Code)

Max Activating Token Index: 276

Text #10

Max Range: 3.4320. Min Range: -3.4320

Max Act: 3.2751. Min Act: -0.1700

Data Index: 1431453 (Python Code)

Max Activating Token Index: 807

Text #11

Max Range: 3.4320. Min Range: -3.4320

Max Act: 3.2751. Min Act: -0.1700

Data Index: 1508217 (Python Code)

Max Activating Token Index: 648

Text #12

Max Range: 3.4320. Min Range: -3.4320

Max Act: 3.2751. Min Act: -0.1700

Data Index: 482644 (C4 (Web Text))

Max Activating Token Index: 129

Text #13

Max Range: 3.4320. Min Range: -3.4320

Max Act: 3.2751. Min Act: -0.1700

Data Index: 17695 (C4 (Web Text))

Max Activating Token Index: 435

Text #14

Max Range: 3.4320. Min Range: -3.4320

Max Act: 3.2908. Min Act: -0.1700

Data Index: 1202037 (C4 (Web Text))

Max Activating Token Index: 503

Text #15

Max Range: 3.4320. Min Range: -3.4320

Max Act: 3.2594. Min Act: -0.1700

Data Index: 706211 (C4 (Web Text))

Max Activating Token Index: 912

Text #16

Max Range: 3.4320. Min Range: -3.4320

Max Act: 3.2751. Min Act: -0.1700

Data Index: 726137 (C4 (Web Text))

Max Activating Token Index: 340

Text #17

Max Range: 3.4320. Min Range: -3.4320

Max Act: 3.2122. Min Act: -0.1700

Data Index: 310258 (C4 (Web Text))

Max Activating Token Index: 598

Text #18

Max Range: 3.4320. Min Range: -3.4320

Max Act: 3.2751. Min Act: -0.1700

Data Index: 703750 (C4 (Web Text))

Max Activating Token Index: 379

Text #19

Max Range: 3.4320. Min Range: -3.4320

Max Act: 3.2751. Min Act: -0.1700

Data Index: 244118 (C4 (Web Text))

Max Activating Token Index: 340