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

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

Neuron 823 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: 5.4054. Min Range: -5.4054

Max Act: 5.4054. Min Act: -0.1700

Data Index: 1066556 (C4 (Web Text))

Max Activating Token Index: 626

Text #1

Max Range: 5.4054. Min Range: -5.4054

Max Act: 5.3273. Min Act: -0.1700

Data Index: 938447 (C4 (Web Text))

Max Activating Token Index: 793

Text #2

Max Range: 5.4054. Min Range: -5.4054

Max Act: 5.0773. Min Act: -0.1700

Data Index: 914306 (C4 (Web Text))

Max Activating Token Index: 685

Text #3

Max Range: 5.4054. Min Range: -5.4054

Max Act: 4.9679. Min Act: -0.1700

Data Index: 413847 (C4 (Web Text))

Max Activating Token Index: 307

Text #4

Max Range: 5.4054. Min Range: -5.4054

Max Act: 4.9679. Min Act: -0.1700

Data Index: 1149932 (C4 (Web Text))

Max Activating Token Index: 517

Text #5

Max Range: 5.4054. Min Range: -5.4054

Max Act: 4.9289. Min Act: -0.1700

Data Index: 377537 (C4 (Web Text))

Max Activating Token Index: 343

Text #6

Max Range: 5.4054. Min Range: -5.4054

Max Act: 4.9132. Min Act: -0.1700

Data Index: 1087836 (C4 (Web Text))

Max Activating Token Index: 545

Text #7

Max Range: 5.4054. Min Range: -5.4054

Max Act: 4.8507. Min Act: -0.1700

Data Index: 1148273 (C4 (Web Text))

Max Activating Token Index: 836

Text #8

Max Range: 5.4054. Min Range: -5.4054

Max Act: 4.8273. Min Act: -0.1700

Data Index: 135150 (C4 (Web Text))

Max Activating Token Index: 957

Text #9

Max Range: 5.4054. Min Range: -5.4054

Max Act: 4.8195. Min Act: -0.1700

Data Index: 349536 (C4 (Web Text))

Max Activating Token Index: 770

Text #10

Max Range: 5.4054. Min Range: -5.4054

Max Act: 4.8351. Min Act: -0.1700

Data Index: 755065 (C4 (Web Text))

Max Activating Token Index: 150

Text #11

Max Range: 5.4054. Min Range: -5.4054

Max Act: 4.7882. Min Act: -0.1700

Data Index: 842837 (C4 (Web Text))

Max Activating Token Index: 913

Text #12

Max Range: 5.4054. Min Range: -5.4054

Max Act: 4.7414. Min Act: -0.1700

Data Index: 997121 (C4 (Web Text))

Max Activating Token Index: 644

Text #13

Max Range: 5.4054. Min Range: -5.4054

Max Act: 4.7570. Min Act: -0.1700

Data Index: 112667 (C4 (Web Text))

Max Activating Token Index: 677

Text #14

Max Range: 5.4054. Min Range: -5.4054

Max Act: 4.7804. Min Act: -0.1700

Data Index: 1242548 (C4 (Web Text))

Max Activating Token Index: 552

Text #15

Max Range: 5.4054. Min Range: -5.4054

Max Act: 4.7023. Min Act: -0.1700

Data Index: 523353 (C4 (Web Text))

Max Activating Token Index: 316

Text #16

Max Range: 5.4054. Min Range: -5.4054

Max Act: 4.7336. Min Act: -0.1699

Data Index: 1063353 (C4 (Web Text))

Max Activating Token Index: 530

Text #17

Max Range: 5.4054. Min Range: -5.4054

Max Act: 4.7804. Min Act: -0.1700

Data Index: 139219 (C4 (Web Text))

Max Activating Token Index: 746

Text #18

Max Range: 5.4054. Min Range: -5.4054

Max Act: 4.7179. Min Act: -0.1700

Data Index: 908315 (C4 (Web Text))

Max Activating Token Index: 598

Text #19

Max Range: 5.4054. Min Range: -5.4054

Max Act: 4.7257. Min Act: -0.1700

Data Index: 593457 (C4 (Web Text))

Max Activating Token Index: 982