Model: GPT-2 Small: 12 Layers, 3072 Neurons per Layer

Dataset: Open Web Text

Neuron 2703 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Hooked Transformer Loading: HookedTransformer.from_pretrained('gpt2-small')

Click the toggle to see the full text!

Text #0

Max Range: 4.4567. Min Range: -4.4567

Max Act: 4.4567. Min Act: -0.1700

Data Index: 3364446 (Open Web Text)

Max Activating Token Index: 536

Text #1

Max Range: 4.4567. Min Range: -4.4567

Max Act: 4.4173. Min Act: -0.1700

Data Index: 4473369 (Open Web Text)

Max Activating Token Index: 284

Text #2

Max Range: 4.4567. Min Range: -4.4567

Max Act: 4.3675. Min Act: -0.1700

Data Index: 3728189 (Open Web Text)

Max Activating Token Index: 139

Text #3

Max Range: 4.4567. Min Range: -4.4567

Max Act: 4.2740. Min Act: -0.1700

Data Index: 3378580 (Open Web Text)

Max Activating Token Index: 601

Text #4

Max Range: 4.4567. Min Range: -4.4567

Max Act: 4.2661. Min Act: -0.1700

Data Index: 3960252 (Open Web Text)

Max Activating Token Index: 789

Text #5

Max Range: 4.4567. Min Range: -4.4567

Max Act: 4.2037. Min Act: -0.1700

Data Index: 2721657 (Open Web Text)

Max Activating Token Index: 186

Text #6

Max Range: 4.4567. Min Range: -4.4567

Max Act: 4.2092. Min Act: -0.1700

Data Index: 684341 (Open Web Text)

Max Activating Token Index: 834

Text #7

Max Range: 4.4567. Min Range: -4.4567

Max Act: 4.1859. Min Act: -0.1700

Data Index: 6061463 (Open Web Text)

Max Activating Token Index: 347

Text #8

Max Range: 4.4567. Min Range: -4.4567

Max Act: 4.2252. Min Act: -0.1700

Data Index: 626138 (Open Web Text)

Max Activating Token Index: 905

Text #9

Max Range: 4.4567. Min Range: -4.4567

Max Act: 4.2048. Min Act: -0.1700

Data Index: 2492447 (Open Web Text)

Max Activating Token Index: 881

Text #10

Max Range: 4.4567. Min Range: -4.4567

Max Act: 4.2269. Min Act: -0.1700

Data Index: 4076763 (Open Web Text)

Max Activating Token Index: 412

Text #11

Max Range: 4.4567. Min Range: -4.4567

Max Act: 4.1637. Min Act: -0.1700

Data Index: 239179 (Open Web Text)

Max Activating Token Index: 830

Text #12

Max Range: 4.4567. Min Range: -4.4567

Max Act: 4.1839. Min Act: -0.1700

Data Index: 1166075 (Open Web Text)

Max Activating Token Index: 384

Text #13

Max Range: 4.4567. Min Range: -4.4567

Max Act: 4.1591. Min Act: -0.1700

Data Index: 4208636 (Open Web Text)

Max Activating Token Index: 331

Text #14

Max Range: 4.4567. Min Range: -4.4567

Max Act: 4.1676. Min Act: -0.1700

Data Index: 418044 (Open Web Text)

Max Activating Token Index: 339

Text #15

Max Range: 4.4567. Min Range: -4.4567

Max Act: 4.1607. Min Act: -0.1700

Data Index: 4224200 (Open Web Text)

Max Activating Token Index: 675

Text #16

Max Range: 4.4567. Min Range: -4.4567

Max Act: 4.1819. Min Act: -0.1700

Data Index: 3736140 (Open Web Text)

Max Activating Token Index: 513

Text #17

Max Range: 4.4567. Min Range: -4.4567

Max Act: 4.1733. Min Act: -0.1700

Data Index: 5433710 (Open Web Text)

Max Activating Token Index: 744

Text #18

Max Range: 4.4567. Min Range: -4.4567

Max Act: 4.1553. Min Act: -0.1700

Data Index: 678519 (Open Web Text)

Max Activating Token Index: 246

Text #19

Max Range: 4.4567. Min Range: -4.4567

Max Act: 4.1293. Min Act: -0.1700

Data Index: 4494860 (Open Web Text)

Max Activating Token Index: 737