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

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

Neuron 276 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: 3.0016. Min Range: -3.0016

Max Act: 3.0016. Min Act: -0.1700

Data Index: 441297 (C4 (Web Text))

Max Activating Token Index: 293

Text #1

Max Range: 3.0016. Min Range: -3.0016

Max Act: 2.9383. Min Act: -0.1700

Data Index: 76856 (C4 (Web Text))

Max Activating Token Index: 504

Text #2

Max Range: 3.0016. Min Range: -3.0016

Max Act: 2.8113. Min Act: -0.1700

Data Index: 1637867 (Python Code)

Max Activating Token Index: 29

Text #3

Max Range: 3.0016. Min Range: -3.0016

Max Act: 2.8113. Min Act: -0.1700

Data Index: 1610558 (Python Code)

Max Activating Token Index: 26

Text #4

Max Range: 3.0016. Min Range: -3.0016

Max Act: 2.8272. Min Act: -0.1700

Data Index: 1124740 (C4 (Web Text))

Max Activating Token Index: 1020

Text #5

Max Range: 3.0016. Min Range: -3.0016

Max Act: 2.8113. Min Act: -0.1700

Data Index: 54631 (C4 (Web Text))

Max Activating Token Index: 913

Text #6

Max Range: 3.0016. Min Range: -3.0016

Max Act: 2.7954. Min Act: -0.1700

Data Index: 416895 (C4 (Web Text))

Max Activating Token Index: 752

Text #7

Max Range: 3.0016. Min Range: -3.0016

Max Act: 2.7794. Min Act: -0.1700

Data Index: 794030 (C4 (Web Text))

Max Activating Token Index: 399

Text #8

Max Range: 3.0016. Min Range: -3.0016

Max Act: 2.7794. Min Act: -0.1700

Data Index: 1364081 (Python Code)

Max Activating Token Index: 770

Text #9

Max Range: 3.0016. Min Range: -3.0016

Max Act: 2.7794. Min Act: -0.1700

Data Index: 203610 (C4 (Web Text))

Max Activating Token Index: 407

Text #10

Max Range: 3.0016. Min Range: -3.0016

Max Act: 2.7635. Min Act: -0.1700

Data Index: 1502706 (Python Code)

Max Activating Token Index: 272

Text #11

Max Range: 3.0016. Min Range: -3.0016

Max Act: 2.7635. Min Act: -0.1700

Data Index: 735416 (C4 (Web Text))

Max Activating Token Index: 495

Text #12

Max Range: 3.0016. Min Range: -3.0016

Max Act: 2.7475. Min Act: -0.1700

Data Index: 1378457 (Python Code)

Max Activating Token Index: 412

Text #13

Max Range: 3.0016. Min Range: -3.0016

Max Act: 2.7475. Min Act: -0.1700

Data Index: 282206 (C4 (Web Text))

Max Activating Token Index: 719

Text #14

Max Range: 3.0016. Min Range: -3.0016

Max Act: 2.7316. Min Act: -0.1700

Data Index: 38996 (C4 (Web Text))

Max Activating Token Index: 669

Text #15

Max Range: 3.0016. Min Range: -3.0016

Max Act: 2.7316. Min Act: -0.1700

Data Index: 615350 (C4 (Web Text))

Max Activating Token Index: 359

Text #16

Max Range: 3.0016. Min Range: -3.0016

Max Act: 2.7156. Min Act: -0.1700

Data Index: 1547221 (Python Code)

Max Activating Token Index: 78

Text #17

Max Range: 3.0016. Min Range: -3.0016

Max Act: 2.7156. Min Act: -0.1700

Data Index: 1520699 (Python Code)

Max Activating Token Index: 39

Text #18

Max Range: 3.0016. Min Range: -3.0016

Max Act: 2.6996. Min Act: -0.1700

Data Index: 1642899 (Python Code)

Max Activating Token Index: 188

Text #19

Max Range: 3.0016. Min Range: -3.0016

Max Act: 2.7156. Min Act: -0.1700

Data Index: 1096366 (C4 (Web Text))

Max Activating Token Index: 53