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

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

Neuron 1366 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: 3.6636. Min Range: -3.6636

Max Act: 3.6636. Min Act: -0.1700

Data Index: 1080498 (C4 (Web Text))

Max Activating Token Index: 701

Text #1

Max Range: 3.6636. Min Range: -3.6636

Max Act: 3.5384. Min Act: -0.1700

Data Index: 582134 (C4 (Web Text))

Max Activating Token Index: 827

Text #2

Max Range: 3.6636. Min Range: -3.6636

Max Act: 3.5384. Min Act: -0.1700

Data Index: 896241 (C4 (Web Text))

Max Activating Token Index: 839

Text #3

Max Range: 3.6636. Min Range: -3.6636

Max Act: 3.5070. Min Act: -0.1700

Data Index: 138114 (C4 (Web Text))

Max Activating Token Index: 298

Text #4

Max Range: 3.6636. Min Range: -3.6636

Max Act: 3.4600. Min Act: -0.1700

Data Index: 18646 (C4 (Web Text))

Max Activating Token Index: 946

Text #5

Max Range: 3.6636. Min Range: -3.6636

Max Act: 3.4287. Min Act: -0.1700

Data Index: 240373 (C4 (Web Text))

Max Activating Token Index: 905

Text #6

Max Range: 3.6636. Min Range: -3.6636

Max Act: 3.4287. Min Act: -0.1700

Data Index: 924071 (C4 (Web Text))

Max Activating Token Index: 567

Text #7

Max Range: 3.6636. Min Range: -3.6636

Max Act: 3.4600. Min Act: -0.1700

Data Index: 1205853 (C4 (Web Text))

Max Activating Token Index: 676

Text #8

Max Range: 3.6636. Min Range: -3.6636

Max Act: 3.4444. Min Act: -0.1700

Data Index: 1152521 (C4 (Web Text))

Max Activating Token Index: 909

Text #9

Max Range: 3.6636. Min Range: -3.6636

Max Act: 3.4130. Min Act: -0.1700

Data Index: 1052471 (C4 (Web Text))

Max Activating Token Index: 284

Text #10

Max Range: 3.6636. Min Range: -3.6636

Max Act: 3.4287. Min Act: -0.1700

Data Index: 702368 (C4 (Web Text))

Max Activating Token Index: 356

Text #11

Max Range: 3.6636. Min Range: -3.6636

Max Act: 3.4287. Min Act: -0.1700

Data Index: 1176426 (C4 (Web Text))

Max Activating Token Index: 443

Text #12

Max Range: 3.6636. Min Range: -3.6636

Max Act: 3.3816. Min Act: -0.1700

Data Index: 843084 (C4 (Web Text))

Max Activating Token Index: 127

Text #13

Max Range: 3.6636. Min Range: -3.6636

Max Act: 3.4130. Min Act: -0.1700

Data Index: 543057 (C4 (Web Text))

Max Activating Token Index: 249

Text #14

Max Range: 3.6636. Min Range: -3.6636

Max Act: 3.3502. Min Act: -0.1700

Data Index: 285315 (C4 (Web Text))

Max Activating Token Index: 669

Text #15

Max Range: 3.6636. Min Range: -3.6636

Max Act: 3.3659. Min Act: -0.1700

Data Index: 562908 (C4 (Web Text))

Max Activating Token Index: 502

Text #16

Max Range: 3.6636. Min Range: -3.6636

Max Act: 3.3345. Min Act: -0.1700

Data Index: 268579 (C4 (Web Text))

Max Activating Token Index: 243

Text #17

Max Range: 3.6636. Min Range: -3.6636

Max Act: 3.3345. Min Act: -0.1700

Data Index: 536129 (C4 (Web Text))

Max Activating Token Index: 221

Text #18

Max Range: 3.6636. Min Range: -3.6636

Max Act: 3.3659. Min Act: -0.1700

Data Index: 48396 (C4 (Web Text))

Max Activating Token Index: 169

Text #19

Max Range: 3.6636. Min Range: -3.6636

Max Act: 3.3345. Min Act: -0.1700

Data Index: 358385 (C4 (Web Text))

Max Activating Token Index: 285