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

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

Neuron 261 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-3l')

Text #0

Max Range: 3.2446. Min Range: -3.2446

Max Act: 3.2289. Min Act: -0.1700

Data Index: 317215 (C4 (Web Text))

Max Activating Token Index: 908

Text #1

Max Range: 3.2446. Min Range: -3.2446

Max Act: 3.2289. Min Act: -0.1700

Data Index: 619671 (C4 (Web Text))

Max Activating Token Index: 781

Text #2

Max Range: 3.2446. Min Range: -3.2446

Max Act: 3.2446. Min Act: -0.1700

Data Index: 474369 (C4 (Web Text))

Max Activating Token Index: 723

Text #3

Max Range: 3.2446. Min Range: -3.2446

Max Act: 3.2132. Min Act: -0.1700

Data Index: 1588255 (Python Code)

Max Activating Token Index: 713

Text #4

Max Range: 3.2446. Min Range: -3.2446

Max Act: 3.1975. Min Act: -0.1700

Data Index: 385364 (C4 (Web Text))

Max Activating Token Index: 537

Text #5

Max Range: 3.2446. Min Range: -3.2446

Max Act: 3.1975. Min Act: -0.1700

Data Index: 35028 (C4 (Web Text))

Max Activating Token Index: 7

Text #6

Max Range: 3.2446. Min Range: -3.2446

Max Act: 3.1817. Min Act: -0.1700

Data Index: 924739 (C4 (Web Text))

Max Activating Token Index: 458

Text #7

Max Range: 3.2446. Min Range: -3.2446

Max Act: 3.1817. Min Act: -0.1700

Data Index: 463321 (C4 (Web Text))

Max Activating Token Index: 9

Text #8

Max Range: 3.2446. Min Range: -3.2446

Max Act: 3.1975. Min Act: -0.1700

Data Index: 264405 (C4 (Web Text))

Max Activating Token Index: 90

Text #9

Max Range: 3.2446. Min Range: -3.2446

Max Act: 3.1975. Min Act: -0.1700

Data Index: 1092328 (C4 (Web Text))

Max Activating Token Index: 782

Text #10

Max Range: 3.2446. Min Range: -3.2446

Max Act: 3.1660. Min Act: -0.1700

Data Index: 892333 (C4 (Web Text))

Max Activating Token Index: 751

Text #11

Max Range: 3.2446. Min Range: -3.2446

Max Act: 3.1660. Min Act: -0.1700

Data Index: 880546 (C4 (Web Text))

Max Activating Token Index: 152

Text #12

Max Range: 3.2446. Min Range: -3.2446

Max Act: 3.1502. Min Act: -0.1700

Data Index: 1263638 (C4 (Web Text))

Max Activating Token Index: 155

Text #13

Max Range: 3.2446. Min Range: -3.2446

Max Act: 3.1817. Min Act: -0.1700

Data Index: 1191055 (C4 (Web Text))

Max Activating Token Index: 264

Text #14

Max Range: 3.2446. Min Range: -3.2446

Max Act: 3.1345. Min Act: -0.1700

Data Index: 1081754 (C4 (Web Text))

Max Activating Token Index: 241

Text #15

Max Range: 3.2446. Min Range: -3.2446

Max Act: 3.1345. Min Act: -0.1700

Data Index: 1267387 (C4 (Web Text))

Max Activating Token Index: 818

Text #16

Max Range: 3.2446. Min Range: -3.2446

Max Act: 3.1660. Min Act: -0.1700

Data Index: 896249 (C4 (Web Text))

Max Activating Token Index: 484

Text #17

Max Range: 3.2446. Min Range: -3.2446

Max Act: 3.1502. Min Act: -0.1700

Data Index: 236296 (C4 (Web Text))

Max Activating Token Index: 331

Text #18

Max Range: 3.2446. Min Range: -3.2446

Max Act: 3.1660. Min Act: -0.1700

Data Index: 593735 (C4 (Web Text))

Max Activating Token Index: 697

Text #19

Max Range: 3.2446. Min Range: -3.2446

Max Act: 3.1502. Min Act: -0.1700

Data Index: 297321 (C4 (Web Text))

Max Activating Token Index: 152