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

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

Neuron 1243 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')

Text #0

Max Range: 3.6148. Min Range: -3.6148

Max Act: 3.6148. Min Act: -0.1700

Data Index: 1625602 (Python Code)

Max Activating Token Index: 779

Text #1

Max Range: 3.6148. Min Range: -3.6148

Max Act: 3.6148. Min Act: -0.1700

Data Index: 1307354 (C4 (Web Text))

Max Activating Token Index: 955

Text #2

Max Range: 3.6148. Min Range: -3.6148

Max Act: 3.5834. Min Act: -0.1700

Data Index: 1126416 (C4 (Web Text))

Max Activating Token Index: 516

Text #3

Max Range: 3.6148. Min Range: -3.6148

Max Act: 3.5521. Min Act: -0.1700

Data Index: 305479 (C4 (Web Text))

Max Activating Token Index: 683

Text #4

Max Range: 3.6148. Min Range: -3.6148

Max Act: 3.5521. Min Act: -0.1700

Data Index: 375818 (C4 (Web Text))

Max Activating Token Index: 161

Text #5

Max Range: 3.6148. Min Range: -3.6148

Max Act: 3.5521. Min Act: -0.1700

Data Index: 1033667 (C4 (Web Text))

Max Activating Token Index: 342

Text #6

Max Range: 3.6148. Min Range: -3.6148

Max Act: 3.5208. Min Act: -0.1700

Data Index: 1484066 (Python Code)

Max Activating Token Index: 847

Text #7

Max Range: 3.6148. Min Range: -3.6148

Max Act: 3.5051. Min Act: -0.1700

Data Index: 1307827 (C4 (Web Text))

Max Activating Token Index: 734

Text #8

Max Range: 3.6148. Min Range: -3.6148

Max Act: 3.5051. Min Act: -0.1700

Data Index: 1572931 (Python Code)

Max Activating Token Index: 139

Text #9

Max Range: 3.6148. Min Range: -3.6148

Max Act: 3.4581. Min Act: -0.1700

Data Index: 80897 (C4 (Web Text))

Max Activating Token Index: 804

Text #10

Max Range: 3.6148. Min Range: -3.6148

Max Act: 3.4738. Min Act: -0.1700

Data Index: 457455 (C4 (Web Text))

Max Activating Token Index: 468

Text #11

Max Range: 3.6148. Min Range: -3.6148

Max Act: 3.4581. Min Act: -0.1700

Data Index: 912109 (C4 (Web Text))

Max Activating Token Index: 536

Text #12

Max Range: 3.6148. Min Range: -3.6148

Max Act: 3.4268. Min Act: -0.1700

Data Index: 300421 (C4 (Web Text))

Max Activating Token Index: 414

Text #13

Max Range: 3.6148. Min Range: -3.6148

Max Act: 3.4581. Min Act: -0.1700

Data Index: 221274 (C4 (Web Text))

Max Activating Token Index: 942

Text #14

Max Range: 3.6148. Min Range: -3.6148

Max Act: 3.4111. Min Act: -0.1700

Data Index: 1101262 (C4 (Web Text))

Max Activating Token Index: 268

Text #15

Max Range: 3.6148. Min Range: -3.6148

Max Act: 3.3954. Min Act: -0.1700

Data Index: 1038117 (C4 (Web Text))

Max Activating Token Index: 270

Text #16

Max Range: 3.6148. Min Range: -3.6148

Max Act: 3.3954. Min Act: -0.1700

Data Index: 855691 (C4 (Web Text))

Max Activating Token Index: 762

Text #17

Max Range: 3.6148. Min Range: -3.6148

Max Act: 3.3483. Min Act: -0.1700

Data Index: 553187 (C4 (Web Text))

Max Activating Token Index: 480

Text #18

Max Range: 3.6148. Min Range: -3.6148

Max Act: 3.4424. Min Act: -0.1700

Data Index: 499079 (C4 (Web Text))

Max Activating Token Index: 734

Text #19

Max Range: 3.6148. Min Range: -3.6148

Max Act: 3.3640. Min Act: -0.1700

Data Index: 406562 (C4 (Web Text))

Max Activating Token Index: 1023