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

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

Neuron 558 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: 3.5153. Min Range: -3.5153

Max Act: 3.5153. Min Act: -0.1700

Data Index: 344931 (C4 (Web Text))

Max Activating Token Index: 801

Text #1

Max Range: 3.5153. Min Range: -3.5153

Max Act: 3.4526. Min Act: -0.1700

Data Index: 1409608 (Python Code)

Max Activating Token Index: 549

Text #2

Max Range: 3.5153. Min Range: -3.5153

Max Act: 3.4056. Min Act: -0.1700

Data Index: 1470989 (Python Code)

Max Activating Token Index: 596

Text #3

Max Range: 3.5153. Min Range: -3.5153

Max Act: 3.3899. Min Act: -0.1700

Data Index: 971926 (C4 (Web Text))

Max Activating Token Index: 755

Text #4

Max Range: 3.5153. Min Range: -3.5153

Max Act: 3.3899. Min Act: -0.1700

Data Index: 1572997 (Python Code)

Max Activating Token Index: 207

Text #5

Max Range: 3.5153. Min Range: -3.5153

Max Act: 3.3742. Min Act: -0.1700

Data Index: 1014263 (C4 (Web Text))

Max Activating Token Index: 667

Text #6

Max Range: 3.5153. Min Range: -3.5153

Max Act: 3.3114. Min Act: -0.1700

Data Index: 458056 (C4 (Web Text))

Max Activating Token Index: 856

Text #7

Max Range: 3.5153. Min Range: -3.5153

Max Act: 3.3428. Min Act: -0.1700

Data Index: 1614731 (Python Code)

Max Activating Token Index: 202

Text #8

Max Range: 3.5153. Min Range: -3.5153

Max Act: 3.3428. Min Act: -0.1700

Data Index: 1576639 (Python Code)

Max Activating Token Index: 422

Text #9

Max Range: 3.5153. Min Range: -3.5153

Max Act: 3.3114. Min Act: -0.1700

Data Index: 656239 (C4 (Web Text))

Max Activating Token Index: 782

Text #10

Max Range: 3.5153. Min Range: -3.5153

Max Act: 3.3428. Min Act: -0.1700

Data Index: 958833 (C4 (Web Text))

Max Activating Token Index: 1009

Text #11

Max Range: 3.5153. Min Range: -3.5153

Max Act: 3.3428. Min Act: -0.1700

Data Index: 1087145 (C4 (Web Text))

Max Activating Token Index: 719

Text #12

Max Range: 3.5153. Min Range: -3.5153

Max Act: 3.3271. Min Act: -0.1700

Data Index: 145491 (C4 (Web Text))

Max Activating Token Index: 645

Text #13

Max Range: 3.5153. Min Range: -3.5153

Max Act: 3.3271. Min Act: -0.1700

Data Index: 1548333 (Python Code)

Max Activating Token Index: 164

Text #14

Max Range: 3.5153. Min Range: -3.5153

Max Act: 3.3271. Min Act: -0.1700

Data Index: 1404584 (Python Code)

Max Activating Token Index: 395

Text #15

Max Range: 3.5153. Min Range: -3.5153

Max Act: 3.2957. Min Act: -0.1700

Data Index: 1401141 (Python Code)

Max Activating Token Index: 346

Text #16

Max Range: 3.5153. Min Range: -3.5153

Max Act: 3.2957. Min Act: -0.1700

Data Index: 1543731 (Python Code)

Max Activating Token Index: 247

Text #17

Max Range: 3.5153. Min Range: -3.5153

Max Act: 3.3271. Min Act: -0.1700

Data Index: 1632692 (Python Code)

Max Activating Token Index: 332

Text #18

Max Range: 3.5153. Min Range: -3.5153

Max Act: 3.3114. Min Act: -0.1700

Data Index: 786941 (C4 (Web Text))

Max Activating Token Index: 676

Text #19

Max Range: 3.5153. Min Range: -3.5153

Max Act: 3.2957. Min Act: -0.1700

Data Index: 112716 (C4 (Web Text))

Max Activating Token Index: 583