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

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

Neuron 165 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.6654. Min Range: -5.6654

Max Act: 5.5717. Min Act: -0.1700

Data Index: 813936 (C4 (Web Text))

Max Activating Token Index: 376

Text #1

Max Range: 5.6654. Min Range: -5.6654

Max Act: 5.6029. Min Act: -0.1700

Data Index: 935839 (C4 (Web Text))

Max Activating Token Index: 139

Text #2

Max Range: 5.6654. Min Range: -5.6654

Max Act: 5.6654. Min Act: -0.1700

Data Index: 222858 (C4 (Web Text))

Max Activating Token Index: 238

Text #3

Max Range: 5.6654. Min Range: -5.6654

Max Act: 5.5717. Min Act: -0.1700

Data Index: 256029 (C4 (Web Text))

Max Activating Token Index: 101

Text #4

Max Range: 5.6654. Min Range: -5.6654

Max Act: 5.5404. Min Act: -0.1700

Data Index: 663592 (C4 (Web Text))

Max Activating Token Index: 199

Text #5

Max Range: 5.6654. Min Range: -5.6654

Max Act: 5.5717. Min Act: -0.1700

Data Index: 379745 (C4 (Web Text))

Max Activating Token Index: 245

Text #6

Max Range: 5.6654. Min Range: -5.6654

Max Act: 5.5092. Min Act: -0.1700

Data Index: 1167448 (C4 (Web Text))

Max Activating Token Index: 188

Text #7

Max Range: 5.6654. Min Range: -5.6654

Max Act: 5.4779. Min Act: -0.1700

Data Index: 489427 (C4 (Web Text))

Max Activating Token Index: 292

Text #8

Max Range: 5.6654. Min Range: -5.6654

Max Act: 5.4779. Min Act: -0.1700

Data Index: 1305587 (C4 (Web Text))

Max Activating Token Index: 725

Text #9

Max Range: 5.6654. Min Range: -5.6654

Max Act: 5.4154. Min Act: -0.1700

Data Index: 1220964 (C4 (Web Text))

Max Activating Token Index: 441

Text #10

Max Range: 5.6654. Min Range: -5.6654

Max Act: 5.4154. Min Act: -0.1700

Data Index: 169943 (C4 (Web Text))

Max Activating Token Index: 311

Text #11

Max Range: 5.6654. Min Range: -5.6654

Max Act: 5.4154. Min Act: -0.1700

Data Index: 574286 (C4 (Web Text))

Max Activating Token Index: 763

Text #12

Max Range: 5.6654. Min Range: -5.6654

Max Act: 5.4154. Min Act: -0.1700

Data Index: 153028 (C4 (Web Text))

Max Activating Token Index: 319

Text #13

Max Range: 5.6654. Min Range: -5.6654

Max Act: 5.3842. Min Act: -0.1700

Data Index: 1251429 (C4 (Web Text))

Max Activating Token Index: 517

Text #14

Max Range: 5.6654. Min Range: -5.6654

Max Act: 5.4154. Min Act: -0.1700

Data Index: 798407 (C4 (Web Text))

Max Activating Token Index: 540

Text #15

Max Range: 5.6654. Min Range: -5.6654

Max Act: 5.3529. Min Act: -0.1700

Data Index: 1330113 (C4 (Web Text))

Max Activating Token Index: 348

Text #16

Max Range: 5.6654. Min Range: -5.6654

Max Act: 5.3842. Min Act: -0.1700

Data Index: 458846 (C4 (Web Text))

Max Activating Token Index: 552

Text #17

Max Range: 5.6654. Min Range: -5.6654

Max Act: 5.4154. Min Act: -0.1700

Data Index: 128318 (C4 (Web Text))

Max Activating Token Index: 191

Text #18

Max Range: 5.6654. Min Range: -5.6654

Max Act: 5.4467. Min Act: -0.1700

Data Index: 818791 (C4 (Web Text))

Max Activating Token Index: 50

Text #19

Max Range: 5.6654. Min Range: -5.6654

Max Act: 5.4154. Min Act: -0.1700

Data Index: 310998 (C4 (Web Text))

Max Activating Token Index: 375