Model: GELU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 1584 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')

Text #0

Max Range: 5.3659. Min Range: -5.3659

Max Act: 5.3346. Min Act: -0.1700

Data Index: 715371 (C4 (Web Text))

Max Activating Token Index: 533

Text #1

Max Range: 5.3659. Min Range: -5.3659

Max Act: 5.3659. Min Act: -0.1700

Data Index: 984810 (C4 (Web Text))

Max Activating Token Index: 789

Text #2

Max Range: 5.3659. Min Range: -5.3659

Max Act: 5.2721. Min Act: -0.1700

Data Index: 798369 (C4 (Web Text))

Max Activating Token Index: 988

Text #3

Max Range: 5.3659. Min Range: -5.3659

Max Act: 5.2721. Min Act: -0.1700

Data Index: 549068 (C4 (Web Text))

Max Activating Token Index: 385

Text #4

Max Range: 5.3659. Min Range: -5.3659

Max Act: 5.1784. Min Act: -0.1700

Data Index: 1063945 (C4 (Web Text))

Max Activating Token Index: 645

Text #5

Max Range: 5.3659. Min Range: -5.3659

Max Act: 5.2096. Min Act: -0.1700

Data Index: 459385 (C4 (Web Text))

Max Activating Token Index: 275

Text #6

Max Range: 5.3659. Min Range: -5.3659

Max Act: 5.1471. Min Act: -0.1700

Data Index: 675516 (C4 (Web Text))

Max Activating Token Index: 168

Text #7

Max Range: 5.3659. Min Range: -5.3659

Max Act: 5.1784. Min Act: -0.1700

Data Index: 554661 (C4 (Web Text))

Max Activating Token Index: 881

Text #8

Max Range: 5.3659. Min Range: -5.3659

Max Act: 5.1471. Min Act: -0.1700

Data Index: 555864 (C4 (Web Text))

Max Activating Token Index: 726

Text #9

Max Range: 5.3659. Min Range: -5.3659

Max Act: 5.1471. Min Act: -0.1700

Data Index: 859947 (C4 (Web Text))

Max Activating Token Index: 542

Text #10

Max Range: 5.3659. Min Range: -5.3659

Max Act: 5.1159. Min Act: -0.1700

Data Index: 851396 (C4 (Web Text))

Max Activating Token Index: 955

Text #11

Max Range: 5.3659. Min Range: -5.3659

Max Act: 5.0534. Min Act: -0.1700

Data Index: 576062 (C4 (Web Text))

Max Activating Token Index: 952

Text #12

Max Range: 5.3659. Min Range: -5.3659

Max Act: 5.0221. Min Act: -0.1700

Data Index: 1339399 (C4 (Web Text))

Max Activating Token Index: 971

Text #13

Max Range: 5.3659. Min Range: -5.3659

Max Act: 5.0846. Min Act: -0.1700

Data Index: 915145 (C4 (Web Text))

Max Activating Token Index: 442

Text #14

Max Range: 5.3659. Min Range: -5.3659

Max Act: 4.9909. Min Act: -0.1700

Data Index: 1333927 (C4 (Web Text))

Max Activating Token Index: 759

Text #15

Max Range: 5.3659. Min Range: -5.3659

Max Act: 5.0221. Min Act: -0.1700

Data Index: 398047 (C4 (Web Text))

Max Activating Token Index: 576

Text #16

Max Range: 5.3659. Min Range: -5.3659

Max Act: 5.0221. Min Act: -0.1700

Data Index: 155036 (C4 (Web Text))

Max Activating Token Index: 805

Text #17

Max Range: 5.3659. Min Range: -5.3659

Max Act: 4.9909. Min Act: -0.1700

Data Index: 1139657 (C4 (Web Text))

Max Activating Token Index: 175

Text #18

Max Range: 5.3659. Min Range: -5.3659

Max Act: 4.9909. Min Act: -0.1700

Data Index: 974246 (C4 (Web Text))

Max Activating Token Index: 844

Text #19

Max Range: 5.3659. Min Range: -5.3659

Max Act: 5.0221. Min Act: -0.1700

Data Index: 289771 (C4 (Web Text))

Max Activating Token Index: 759