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

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

Neuron 137 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: 5.8152. Min Range: -5.8152

Max Act: 5.8152. Min Act: -0.1700

Data Index: 559089 (C4 (Web Text))

Max Activating Token Index: 102

Text #1

Max Range: 5.8152. Min Range: -5.8152

Max Act: 5.8152. Min Act: -0.1700

Data Index: 1315307 (C4 (Web Text))

Max Activating Token Index: 427

Text #2

Max Range: 5.8152. Min Range: -5.8152

Max Act: 5.7527. Min Act: -0.1700

Data Index: 266623 (C4 (Web Text))

Max Activating Token Index: 477

Text #3

Max Range: 5.8152. Min Range: -5.8152

Max Act: 5.6589. Min Act: -0.1700

Data Index: 118048 (C4 (Web Text))

Max Activating Token Index: 353

Text #4

Max Range: 5.8152. Min Range: -5.8152

Max Act: 5.6902. Min Act: -0.1700

Data Index: 1284083 (C4 (Web Text))

Max Activating Token Index: 254

Text #5

Max Range: 5.8152. Min Range: -5.8152

Max Act: 5.7214. Min Act: -0.1700

Data Index: 1126059 (C4 (Web Text))

Max Activating Token Index: 559

Text #6

Max Range: 5.8152. Min Range: -5.8152

Max Act: 5.6902. Min Act: -0.1700

Data Index: 479880 (C4 (Web Text))

Max Activating Token Index: 394

Text #7

Max Range: 5.8152. Min Range: -5.8152

Max Act: 5.6277. Min Act: -0.1700

Data Index: 920532 (C4 (Web Text))

Max Activating Token Index: 640

Text #8

Max Range: 5.8152. Min Range: -5.8152

Max Act: 5.6277. Min Act: -0.1700

Data Index: 184362 (C4 (Web Text))

Max Activating Token Index: 271

Text #9

Max Range: 5.8152. Min Range: -5.8152

Max Act: 5.5652. Min Act: -0.1700

Data Index: 867664 (C4 (Web Text))

Max Activating Token Index: 510

Text #10

Max Range: 5.8152. Min Range: -5.8152

Max Act: 5.5339. Min Act: -0.1700

Data Index: 1036253 (C4 (Web Text))

Max Activating Token Index: 163

Text #11

Max Range: 5.8152. Min Range: -5.8152

Max Act: 5.5964. Min Act: -0.1700

Data Index: 54515 (C4 (Web Text))

Max Activating Token Index: 482

Text #12

Max Range: 5.8152. Min Range: -5.8152

Max Act: 5.6589. Min Act: -0.1700

Data Index: 86659 (C4 (Web Text))

Max Activating Token Index: 696

Text #13

Max Range: 5.8152. Min Range: -5.8152

Max Act: 5.5964. Min Act: -0.1700

Data Index: 140023 (C4 (Web Text))

Max Activating Token Index: 711

Text #14

Max Range: 5.8152. Min Range: -5.8152

Max Act: 5.5652. Min Act: -0.1700

Data Index: 254585 (C4 (Web Text))

Max Activating Token Index: 378

Text #15

Max Range: 5.8152. Min Range: -5.8152

Max Act: 5.5964. Min Act: -0.1700

Data Index: 374577 (C4 (Web Text))

Max Activating Token Index: 367

Text #16

Max Range: 5.8152. Min Range: -5.8152

Max Act: 5.5652. Min Act: -0.1700

Data Index: 408092 (C4 (Web Text))

Max Activating Token Index: 305

Text #17

Max Range: 5.8152. Min Range: -5.8152

Max Act: 5.5339. Min Act: -0.1700

Data Index: 953801 (C4 (Web Text))

Max Activating Token Index: 432

Text #18

Max Range: 5.8152. Min Range: -5.8152

Max Act: 5.5027. Min Act: -0.1700

Data Index: 437380 (C4 (Web Text))

Max Activating Token Index: 435

Text #19

Max Range: 5.8152. Min Range: -5.8152

Max Act: 5.5652. Min Act: -0.1700

Data Index: 457074 (C4 (Web Text))

Max Activating Token Index: 424