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

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

Neuron 334 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.1784. Min Range: -3.1784

Max Act: 3.1784. Min Act: -0.1700

Data Index: 214131 (C4 (Web Text))

Max Activating Token Index: 868

Text #1

Max Range: 3.1784. Min Range: -3.1784

Max Act: 3.1627. Min Act: -0.1700

Data Index: 630629 (C4 (Web Text))

Max Activating Token Index: 467

Text #2

Max Range: 3.1784. Min Range: -3.1784

Max Act: 3.0997. Min Act: -0.1700

Data Index: 554266 (C4 (Web Text))

Max Activating Token Index: 942

Text #3

Max Range: 3.1784. Min Range: -3.1784

Max Act: 3.1154. Min Act: -0.1700

Data Index: 848592 (C4 (Web Text))

Max Activating Token Index: 200

Text #4

Max Range: 3.1784. Min Range: -3.1784

Max Act: 3.0839. Min Act: -0.1700

Data Index: 153000 (C4 (Web Text))

Max Activating Token Index: 654

Text #5

Max Range: 3.1784. Min Range: -3.1784

Max Act: 3.0997. Min Act: -0.1700

Data Index: 833085 (C4 (Web Text))

Max Activating Token Index: 465

Text #6

Max Range: 3.1784. Min Range: -3.1784

Max Act: 3.0997. Min Act: -0.1700

Data Index: 733824 (C4 (Web Text))

Max Activating Token Index: 377

Text #7

Max Range: 3.1784. Min Range: -3.1784

Max Act: 3.0839. Min Act: -0.1700

Data Index: 360137 (C4 (Web Text))

Max Activating Token Index: 656

Text #8

Max Range: 3.1784. Min Range: -3.1784

Max Act: 3.0681. Min Act: -0.1700

Data Index: 60448 (C4 (Web Text))

Max Activating Token Index: 691

Text #9

Max Range: 3.1784. Min Range: -3.1784

Max Act: 3.0681. Min Act: -0.1700

Data Index: 824655 (C4 (Web Text))

Max Activating Token Index: 588

Text #10

Max Range: 3.1784. Min Range: -3.1784

Max Act: 3.0523. Min Act: -0.1700

Data Index: 1202726 (C4 (Web Text))

Max Activating Token Index: 705

Text #11

Max Range: 3.1784. Min Range: -3.1784

Max Act: 3.0681. Min Act: -0.1700

Data Index: 366267 (C4 (Web Text))

Max Activating Token Index: 621

Text #12

Max Range: 3.1784. Min Range: -3.1784

Max Act: 3.0366. Min Act: -0.1700

Data Index: 965006 (C4 (Web Text))

Max Activating Token Index: 542

Text #13

Max Range: 3.1784. Min Range: -3.1784

Max Act: 3.0366. Min Act: -0.1700

Data Index: 295009 (C4 (Web Text))

Max Activating Token Index: 784

Text #14

Max Range: 3.1784. Min Range: -3.1784

Max Act: 3.0366. Min Act: -0.1700

Data Index: 953963 (C4 (Web Text))

Max Activating Token Index: 957

Text #15

Max Range: 3.1784. Min Range: -3.1784

Max Act: 3.0050. Min Act: -0.1700

Data Index: 377281 (C4 (Web Text))

Max Activating Token Index: 265

Text #16

Max Range: 3.1784. Min Range: -3.1784

Max Act: 2.9891. Min Act: -0.1700

Data Index: 1015479 (C4 (Web Text))

Max Activating Token Index: 1023

Text #17

Max Range: 3.1784. Min Range: -3.1784

Max Act: 3.0050. Min Act: -0.1700

Data Index: 334239 (C4 (Web Text))

Max Activating Token Index: 513

Text #18

Max Range: 3.1784. Min Range: -3.1784

Max Act: 2.9891. Min Act: -0.1700

Data Index: 662365 (C4 (Web Text))

Max Activating Token Index: 628

Text #19

Max Range: 3.1784. Min Range: -3.1784

Max Act: 2.9575. Min Act: -0.1700

Data Index: 922419 (C4 (Web Text))

Max Activating Token Index: 266