Model: GELU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 517 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-3l')

Text #0

Max Range: 3.9999. Min Range: -3.9999

Max Act: 3.9999. Min Act: -0.1700

Data Index: 1015951 (C4 (Web Text))

Max Activating Token Index: 418

Text #1

Max Range: 3.9999. Min Range: -3.9999

Max Act: 3.9374. Min Act: -0.1700

Data Index: 850618 (C4 (Web Text))

Max Activating Token Index: 39

Text #2

Max Range: 3.9999. Min Range: -3.9999

Max Act: 3.9061. Min Act: -0.1700

Data Index: 1210737 (C4 (Web Text))

Max Activating Token Index: 431

Text #3

Max Range: 3.9999. Min Range: -3.9999

Max Act: 3.9061. Min Act: -0.1700

Data Index: 560162 (C4 (Web Text))

Max Activating Token Index: 11

Text #4

Max Range: 3.9999. Min Range: -3.9999

Max Act: 3.9374. Min Act: -0.1700

Data Index: 623638 (C4 (Web Text))

Max Activating Token Index: 632

Text #5

Max Range: 3.9999. Min Range: -3.9999

Max Act: 3.8748. Min Act: -0.1700

Data Index: 31427 (C4 (Web Text))

Max Activating Token Index: 427

Text #6

Max Range: 3.9999. Min Range: -3.9999

Max Act: 3.8436. Min Act: -0.1700

Data Index: 84478 (C4 (Web Text))

Max Activating Token Index: 816

Text #7

Max Range: 3.9999. Min Range: -3.9999

Max Act: 3.8436. Min Act: -0.1700

Data Index: 1301358 (C4 (Web Text))

Max Activating Token Index: 760

Text #8

Max Range: 3.9999. Min Range: -3.9999

Max Act: 3.8436. Min Act: -0.1700

Data Index: 386801 (C4 (Web Text))

Max Activating Token Index: 116

Text #9

Max Range: 3.9999. Min Range: -3.9999

Max Act: 3.8748. Min Act: -0.1700

Data Index: 838142 (C4 (Web Text))

Max Activating Token Index: 434

Text #10

Max Range: 3.9999. Min Range: -3.9999

Max Act: 3.7184. Min Act: -0.1700

Data Index: 158830 (C4 (Web Text))

Max Activating Token Index: 789

Text #11

Max Range: 3.9999. Min Range: -3.9999

Max Act: 3.8123. Min Act: -0.1700

Data Index: 382083 (C4 (Web Text))

Max Activating Token Index: 864

Text #12

Max Range: 3.9999. Min Range: -3.9999

Max Act: 3.8123. Min Act: -0.1700

Data Index: 115244 (C4 (Web Text))

Max Activating Token Index: 33

Text #13

Max Range: 3.9999. Min Range: -3.9999

Max Act: 3.8436. Min Act: -0.1700

Data Index: 495418 (C4 (Web Text))

Max Activating Token Index: 60

Text #14

Max Range: 3.9999. Min Range: -3.9999

Max Act: 3.8436. Min Act: -0.1700

Data Index: 1142365 (C4 (Web Text))

Max Activating Token Index: 584

Text #15

Max Range: 3.9999. Min Range: -3.9999

Max Act: 3.8123. Min Act: -0.1700

Data Index: 769013 (C4 (Web Text))

Max Activating Token Index: 625

Text #16

Max Range: 3.9999. Min Range: -3.9999

Max Act: 3.7497. Min Act: -0.1700

Data Index: 180378 (C4 (Web Text))

Max Activating Token Index: 549

Text #17

Max Range: 3.9999. Min Range: -3.9999

Max Act: 3.7497. Min Act: -0.1700

Data Index: 1284519 (C4 (Web Text))

Max Activating Token Index: 179

Text #18

Max Range: 3.9999. Min Range: -3.9999

Max Act: 3.9061. Min Act: -0.1700

Data Index: 697401 (C4 (Web Text))

Max Activating Token Index: 456

Text #19

Max Range: 3.9999. Min Range: -3.9999

Max Act: 3.7810. Min Act: -0.1700

Data Index: 526894 (C4 (Web Text))

Max Activating Token Index: 334