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

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

Neuron 693 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: 3.6879. Min Range: -3.6879

Max Act: 3.6879. Min Act: -0.1700

Data Index: 1024942 (C4 (Web Text))

Max Activating Token Index: 730

Text #1

Max Range: 3.6879. Min Range: -3.6879

Max Act: 3.6253. Min Act: -0.1700

Data Index: 922742 (C4 (Web Text))

Max Activating Token Index: 457

Text #2

Max Range: 3.6879. Min Range: -3.6879

Max Act: 3.6097. Min Act: -0.1700

Data Index: 525627 (C4 (Web Text))

Max Activating Token Index: 202

Text #3

Max Range: 3.6879. Min Range: -3.6879

Max Act: 3.5940. Min Act: -0.1700

Data Index: 914635 (C4 (Web Text))

Max Activating Token Index: 295

Text #4

Max Range: 3.6879. Min Range: -3.6879

Max Act: 3.5783. Min Act: -0.1700

Data Index: 975986 (C4 (Web Text))

Max Activating Token Index: 168

Text #5

Max Range: 3.6879. Min Range: -3.6879

Max Act: 3.5940. Min Act: -0.1700

Data Index: 988182 (C4 (Web Text))

Max Activating Token Index: 426

Text #6

Max Range: 3.6879. Min Range: -3.6879

Max Act: 3.5783. Min Act: -0.1700

Data Index: 706971 (C4 (Web Text))

Max Activating Token Index: 103

Text #7

Max Range: 3.6879. Min Range: -3.6879

Max Act: 3.5470. Min Act: -0.1700

Data Index: 1198601 (C4 (Web Text))

Max Activating Token Index: 841

Text #8

Max Range: 3.6879. Min Range: -3.6879

Max Act: 3.5470. Min Act: -0.1700

Data Index: 1160286 (C4 (Web Text))

Max Activating Token Index: 431

Text #9

Max Range: 3.6879. Min Range: -3.6879

Max Act: 3.5314. Min Act: -0.1700

Data Index: 394314 (C4 (Web Text))

Max Activating Token Index: 48

Text #10

Max Range: 3.6879. Min Range: -3.6879

Max Act: 3.5157. Min Act: -0.1700

Data Index: 975877 (C4 (Web Text))

Max Activating Token Index: 465

Text #11

Max Range: 3.6879. Min Range: -3.6879

Max Act: 3.5157. Min Act: -0.1700

Data Index: 1285109 (C4 (Web Text))

Max Activating Token Index: 56

Text #12

Max Range: 3.6879. Min Range: -3.6879

Max Act: 3.5157. Min Act: -0.1700

Data Index: 801642 (C4 (Web Text))

Max Activating Token Index: 202

Text #13

Max Range: 3.6879. Min Range: -3.6879

Max Act: 3.5157. Min Act: -0.1700

Data Index: 1028696 (C4 (Web Text))

Max Activating Token Index: 193

Text #14

Max Range: 3.6879. Min Range: -3.6879

Max Act: 3.5000. Min Act: -0.1700

Data Index: 670058 (C4 (Web Text))

Max Activating Token Index: 709

Text #15

Max Range: 3.6879. Min Range: -3.6879

Max Act: 3.5000. Min Act: -0.1700

Data Index: 1338992 (C4 (Web Text))

Max Activating Token Index: 298

Text #16

Max Range: 3.6879. Min Range: -3.6879

Max Act: 3.5157. Min Act: -0.1700

Data Index: 420649 (C4 (Web Text))

Max Activating Token Index: 335

Text #17

Max Range: 3.6879. Min Range: -3.6879

Max Act: 3.5000. Min Act: -0.1700

Data Index: 1266561 (C4 (Web Text))

Max Activating Token Index: 886

Text #18

Max Range: 3.6879. Min Range: -3.6879

Max Act: 3.5000. Min Act: -0.1700

Data Index: 1195575 (C4 (Web Text))

Max Activating Token Index: 613

Text #19

Max Range: 3.6879. Min Range: -3.6879

Max Act: 3.5000. Min Act: -0.1700

Data Index: 943548 (C4 (Web Text))

Max Activating Token Index: 42