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

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

Neuron 1533 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: 5.7573. Min Range: -5.7573

Max Act: 5.7573. Min Act: -0.1700

Data Index: 761557 (C4 (Web Text))

Max Activating Token Index: 487

Text #1

Max Range: 5.7573. Min Range: -5.7573

Max Act: 5.6948. Min Act: -0.1700

Data Index: 998954 (C4 (Web Text))

Max Activating Token Index: 569

Text #2

Max Range: 5.7573. Min Range: -5.7573

Max Act: 5.6323. Min Act: -0.1699

Data Index: 456231 (C4 (Web Text))

Max Activating Token Index: 779

Text #3

Max Range: 5.7573. Min Range: -5.7573

Max Act: 5.6011. Min Act: -0.1700

Data Index: 55549 (C4 (Web Text))

Max Activating Token Index: 770

Text #4

Max Range: 5.7573. Min Range: -5.7573

Max Act: 5.5073. Min Act: -0.1700

Data Index: 1267307 (C4 (Web Text))

Max Activating Token Index: 198

Text #5

Max Range: 5.7573. Min Range: -5.7573

Max Act: 5.5698. Min Act: -0.1700

Data Index: 1350486 (C4 (Web Text))

Max Activating Token Index: 442

Text #6

Max Range: 5.7573. Min Range: -5.7573

Max Act: 5.4761. Min Act: -0.1700

Data Index: 481711 (C4 (Web Text))

Max Activating Token Index: 961

Text #7

Max Range: 5.7573. Min Range: -5.7573

Max Act: 5.4448. Min Act: -0.1700

Data Index: 799017 (C4 (Web Text))

Max Activating Token Index: 654

Text #8

Max Range: 5.7573. Min Range: -5.7573

Max Act: 5.4448. Min Act: -0.1685

Data Index: 609762 (C4 (Web Text))

Max Activating Token Index: 618

Text #9

Max Range: 5.7573. Min Range: -5.7573

Max Act: 5.4136. Min Act: -0.1698

Data Index: 1009244 (C4 (Web Text))

Max Activating Token Index: 613

Text #10

Max Range: 5.7573. Min Range: -5.7573

Max Act: 5.4136. Min Act: -0.1699

Data Index: 522075 (C4 (Web Text))

Max Activating Token Index: 154

Text #11

Max Range: 5.7573. Min Range: -5.7573

Max Act: 5.4136. Min Act: -0.1640

Data Index: 44502 (C4 (Web Text))

Max Activating Token Index: 259

Text #12

Max Range: 5.7573. Min Range: -5.7573

Max Act: 5.3511. Min Act: -0.1700

Data Index: 1116243 (C4 (Web Text))

Max Activating Token Index: 559

Text #13

Max Range: 5.7573. Min Range: -5.7573

Max Act: 5.3823. Min Act: -0.1671

Data Index: 230050 (C4 (Web Text))

Max Activating Token Index: 249

Text #14

Max Range: 5.7573. Min Range: -5.7573

Max Act: 5.3823. Min Act: -0.1700

Data Index: 321191 (C4 (Web Text))

Max Activating Token Index: 929

Text #15

Max Range: 5.7573. Min Range: -5.7573

Max Act: 5.4136. Min Act: -0.1700

Data Index: 1185205 (C4 (Web Text))

Max Activating Token Index: 320

Text #16

Max Range: 5.7573. Min Range: -5.7573

Max Act: 5.3198. Min Act: -0.1700

Data Index: 1187534 (C4 (Web Text))

Max Activating Token Index: 482

Text #17

Max Range: 5.7573. Min Range: -5.7573

Max Act: 5.3198. Min Act: -0.1700

Data Index: 268836 (C4 (Web Text))

Max Activating Token Index: 101

Text #18

Max Range: 5.7573. Min Range: -5.7573

Max Act: 5.2261. Min Act: -0.1700

Data Index: 506568 (C4 (Web Text))

Max Activating Token Index: 1017

Text #19

Max Range: 5.7573. Min Range: -5.7573

Max Act: 5.2886. Min Act: -0.1700

Data Index: 1033169 (C4 (Web Text))

Max Activating Token Index: 183