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

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

Neuron 1203 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: 11.2143. Min Range: -11.2143

Max Act: 11.2143. Min Act: -0.1700

Data Index: 695998 (C4 (Web Text))

Max Activating Token Index: 298

Text #1

Max Range: 11.2143. Min Range: -11.2143

Max Act: 10.6518. Min Act: -0.1700

Data Index: 1055420 (C4 (Web Text))

Max Activating Token Index: 945

Text #2

Max Range: 11.2143. Min Range: -11.2143

Max Act: 10.7143. Min Act: -0.1700

Data Index: 1212263 (C4 (Web Text))

Max Activating Token Index: 730

Text #3

Max Range: 11.2143. Min Range: -11.2143

Max Act: 10.7768. Min Act: -0.1700

Data Index: 1035366 (C4 (Web Text))

Max Activating Token Index: 24

Text #4

Max Range: 11.2143. Min Range: -11.2143

Max Act: 10.7768. Min Act: -0.1700

Data Index: 258419 (C4 (Web Text))

Max Activating Token Index: 709

Text #5

Max Range: 11.2143. Min Range: -11.2143

Max Act: 10.5893. Min Act: -0.1700

Data Index: 1329304 (C4 (Web Text))

Max Activating Token Index: 617

Text #6

Max Range: 11.2143. Min Range: -11.2143

Max Act: 10.0893. Min Act: -0.1700

Data Index: 878410 (C4 (Web Text))

Max Activating Token Index: 257

Text #7

Max Range: 11.2143. Min Range: -11.2143

Max Act: 9.9018. Min Act: -0.1700

Data Index: 1327151 (C4 (Web Text))

Max Activating Token Index: 283

Text #8

Max Range: 11.2143. Min Range: -11.2143

Max Act: 10.2143. Min Act: -0.1700

Data Index: 573214 (C4 (Web Text))

Max Activating Token Index: 898

Text #9

Max Range: 11.2143. Min Range: -11.2143

Max Act: 9.9018. Min Act: -0.1700

Data Index: 424476 (C4 (Web Text))

Max Activating Token Index: 680

Text #10

Max Range: 11.2143. Min Range: -11.2143

Max Act: 9.8393. Min Act: -0.1700

Data Index: 867066 (C4 (Web Text))

Max Activating Token Index: 1014

Text #11

Max Range: 11.2143. Min Range: -11.2143

Max Act: 9.9643. Min Act: -0.1700

Data Index: 227236 (C4 (Web Text))

Max Activating Token Index: 422

Text #12

Max Range: 11.2143. Min Range: -11.2143

Max Act: 10.0268. Min Act: -0.1700

Data Index: 1048965 (C4 (Web Text))

Max Activating Token Index: 427

Text #13

Max Range: 11.2143. Min Range: -11.2143

Max Act: 9.7143. Min Act: -0.1700

Data Index: 543138 (C4 (Web Text))

Max Activating Token Index: 625

Text #14

Max Range: 11.2143. Min Range: -11.2143

Max Act: 10.0893. Min Act: -0.1700

Data Index: 938612 (C4 (Web Text))

Max Activating Token Index: 471

Text #15

Max Range: 11.2143. Min Range: -11.2143

Max Act: 9.7768. Min Act: -0.1700

Data Index: 1005173 (C4 (Web Text))

Max Activating Token Index: 421

Text #16

Max Range: 11.2143. Min Range: -11.2143

Max Act: 9.4643. Min Act: -0.1700

Data Index: 1017288 (C4 (Web Text))

Max Activating Token Index: 683

Text #17

Max Range: 11.2143. Min Range: -11.2143

Max Act: 9.4643. Min Act: -0.1700

Data Index: 523230 (C4 (Web Text))

Max Activating Token Index: 820

Text #18

Max Range: 11.2143. Min Range: -11.2143

Max Act: 9.4018. Min Act: -0.1700

Data Index: 1246350 (C4 (Web Text))

Max Activating Token Index: 385

Text #19

Max Range: 11.2143. Min Range: -11.2143

Max Act: 9.6518. Min Act: -0.1700

Data Index: 1003278 (C4 (Web Text))

Max Activating Token Index: 1021