Model: GELU Model: 1 Layers, 2048 Neurons per Layer

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

Neuron 628 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Hooked Transformer Loading: HookedTransformer.from_pretrained('gelu-1l')

Click the toggle to see the full text!

Text #0

Max Range: 3.4539. Min Range: -3.4539

Max Act: 3.4539. Min Act: -0.1700

Data Index: 1019265 (C4 (Web Text))

Max Activating Token Index: 984

Text #1

Max Range: 3.4539. Min Range: -3.4539

Max Act: 3.4040. Min Act: -0.1700

Data Index: 1458834 (Python Code)

Max Activating Token Index: 570

Text #2

Max Range: 3.4539. Min Range: -3.4539

Max Act: 3.2654. Min Act: -0.1700

Data Index: 854910 (C4 (Web Text))

Max Activating Token Index: 282

Text #3

Max Range: 3.4539. Min Range: -3.4539

Max Act: 3.2559. Min Act: -0.1700

Data Index: 487208 (C4 (Web Text))

Max Activating Token Index: 627

Text #4

Max Range: 3.4539. Min Range: -3.4539

Max Act: 3.2710. Min Act: -0.1700

Data Index: 596178 (C4 (Web Text))

Max Activating Token Index: 302

Text #5

Max Range: 3.4539. Min Range: -3.4539

Max Act: 3.2277. Min Act: -0.1700

Data Index: 578389 (C4 (Web Text))

Max Activating Token Index: 863

Text #6

Max Range: 3.4539. Min Range: -3.4539

Max Act: 3.2551. Min Act: -0.1700

Data Index: 1025890 (C4 (Web Text))

Max Activating Token Index: 288

Text #7

Max Range: 3.4539. Min Range: -3.4539

Max Act: 3.2358. Min Act: -0.1700

Data Index: 1136914 (C4 (Web Text))

Max Activating Token Index: 216

Text #8

Max Range: 3.4539. Min Range: -3.4539

Max Act: 3.2254. Min Act: -0.1700

Data Index: 437592 (C4 (Web Text))

Max Activating Token Index: 315

Text #9

Max Range: 3.4539. Min Range: -3.4539

Max Act: 3.2311. Min Act: -0.1700

Data Index: 675957 (C4 (Web Text))

Max Activating Token Index: 601

Text #10

Max Range: 3.4539. Min Range: -3.4539

Max Act: 3.2131. Min Act: -0.1700

Data Index: 498971 (C4 (Web Text))

Max Activating Token Index: 937

Text #11

Max Range: 3.4539. Min Range: -3.4539

Max Act: 3.2096. Min Act: -0.1700

Data Index: 257499 (C4 (Web Text))

Max Activating Token Index: 188

Text #12

Max Range: 3.4539. Min Range: -3.4539

Max Act: 3.2021. Min Act: -0.1700

Data Index: 1020089 (C4 (Web Text))

Max Activating Token Index: 620

Text #13

Max Range: 3.4539. Min Range: -3.4539

Max Act: 3.1867. Min Act: -0.1700

Data Index: 687072 (C4 (Web Text))

Max Activating Token Index: 610

Text #14

Max Range: 3.4539. Min Range: -3.4539

Max Act: 3.1988. Min Act: -0.1700

Data Index: 464997 (C4 (Web Text))

Max Activating Token Index: 462

Text #15

Max Range: 3.4539. Min Range: -3.4539

Max Act: 3.1630. Min Act: -0.1700

Data Index: 908077 (C4 (Web Text))

Max Activating Token Index: 64

Text #16

Max Range: 3.4539. Min Range: -3.4539

Max Act: 3.1940. Min Act: -0.1700

Data Index: 1064976 (C4 (Web Text))

Max Activating Token Index: 543

Text #17

Max Range: 3.4539. Min Range: -3.4539

Max Act: 3.1655. Min Act: -0.1700

Data Index: 1020130 (C4 (Web Text))

Max Activating Token Index: 25

Text #18

Max Range: 3.4539. Min Range: -3.4539

Max Act: 3.1454. Min Act: -0.1700

Data Index: 362271 (C4 (Web Text))

Max Activating Token Index: 753

Text #19

Max Range: 3.4539. Min Range: -3.4539

Max Act: 3.1735. Min Act: -0.1700

Data Index: 903469 (C4 (Web Text))

Max Activating Token Index: 906