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

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

Neuron 537 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: 5.5441. Min Range: -5.5441

Max Act: 5.5441. Min Act: -0.1700

Data Index: 60585 (C4 (Web Text))

Max Activating Token Index: 873

Text #1

Max Range: 5.5441. Min Range: -5.5441

Max Act: 5.4816. Min Act: -0.1700

Data Index: 1123711 (C4 (Web Text))

Max Activating Token Index: 373

Text #2

Max Range: 5.5441. Min Range: -5.5441

Max Act: 5.2941. Min Act: -0.1700

Data Index: 409024 (C4 (Web Text))

Max Activating Token Index: 131

Text #3

Max Range: 5.5441. Min Range: -5.5441

Max Act: 5.3254. Min Act: -0.1700

Data Index: 274179 (C4 (Web Text))

Max Activating Token Index: 15

Text #4

Max Range: 5.5441. Min Range: -5.5441

Max Act: 5.2629. Min Act: -0.1700

Data Index: 399712 (C4 (Web Text))

Max Activating Token Index: 204

Text #5

Max Range: 5.5441. Min Range: -5.5441

Max Act: 5.3254. Min Act: -0.1700

Data Index: 285191 (C4 (Web Text))

Max Activating Token Index: 782

Text #6

Max Range: 5.5441. Min Range: -5.5441

Max Act: 5.2316. Min Act: -0.1700

Data Index: 602463 (C4 (Web Text))

Max Activating Token Index: 153

Text #7

Max Range: 5.5441. Min Range: -5.5441

Max Act: 5.2316. Min Act: -0.1700

Data Index: 306696 (C4 (Web Text))

Max Activating Token Index: 403

Text #8

Max Range: 5.5441. Min Range: -5.5441

Max Act: 5.2316. Min Act: -0.1700

Data Index: 517573 (C4 (Web Text))

Max Activating Token Index: 32

Text #9

Max Range: 5.5441. Min Range: -5.5441

Max Act: 5.2004. Min Act: -0.1700

Data Index: 1096295 (C4 (Web Text))

Max Activating Token Index: 234

Text #10

Max Range: 5.5441. Min Range: -5.5441

Max Act: 5.1691. Min Act: -0.1700

Data Index: 512544 (C4 (Web Text))

Max Activating Token Index: 933

Text #11

Max Range: 5.5441. Min Range: -5.5441

Max Act: 5.1379. Min Act: -0.1700

Data Index: 1127711 (C4 (Web Text))

Max Activating Token Index: 174

Text #12

Max Range: 5.5441. Min Range: -5.5441

Max Act: 5.1066. Min Act: -0.1700

Data Index: 8676 (C4 (Web Text))

Max Activating Token Index: 328

Text #13

Max Range: 5.5441. Min Range: -5.5441

Max Act: 5.1691. Min Act: -0.1700

Data Index: 607628 (C4 (Web Text))

Max Activating Token Index: 219

Text #14

Max Range: 5.5441. Min Range: -5.5441

Max Act: 5.1066. Min Act: -0.1700

Data Index: 1096361 (C4 (Web Text))

Max Activating Token Index: 36

Text #15

Max Range: 5.5441. Min Range: -5.5441

Max Act: 5.0754. Min Act: -0.1700

Data Index: 1252641 (C4 (Web Text))

Max Activating Token Index: 916

Text #16

Max Range: 5.5441. Min Range: -5.5441

Max Act: 5.1691. Min Act: -0.1700

Data Index: 840516 (C4 (Web Text))

Max Activating Token Index: 324

Text #17

Max Range: 5.5441. Min Range: -5.5441

Max Act: 5.0754. Min Act: -0.1700

Data Index: 320103 (C4 (Web Text))

Max Activating Token Index: 464

Text #18

Max Range: 5.5441. Min Range: -5.5441

Max Act: 5.0441. Min Act: -0.1700

Data Index: 886676 (C4 (Web Text))

Max Activating Token Index: 319

Text #19

Max Range: 5.5441. Min Range: -5.5441

Max Act: 5.1691. Min Act: -0.1700

Data Index: 27002 (C4 (Web Text))

Max Activating Token Index: 722