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

Dataset: Open Web Text

Neuron 1605 in Layer 3

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: 4.8671. Min Range: -4.8671

Max Act: 4.8671. Min Act: -0.1697

Data Index: 8077680 (Open Web Text)

Max Activating Token Index: 657

Text #1

Max Range: 4.8671. Min Range: -4.8671

Max Act: 4.8362. Min Act: -0.1700

Data Index: 676457 (Open Web Text)

Max Activating Token Index: 341

Text #2

Max Range: 4.8671. Min Range: -4.8671

Max Act: 4.6713. Min Act: -0.1700

Data Index: 2096826 (Open Web Text)

Max Activating Token Index: 628

Text #3

Max Range: 4.8671. Min Range: -4.8671

Max Act: 4.6460. Min Act: -0.1697

Data Index: 5028540 (Open Web Text)

Max Activating Token Index: 698

Text #4

Max Range: 4.8671. Min Range: -4.8671

Max Act: 4.5496. Min Act: -0.1700

Data Index: 451688 (Open Web Text)

Max Activating Token Index: 869

Text #5

Max Range: 4.8671. Min Range: -4.8671

Max Act: 4.5426. Min Act: -0.1700

Data Index: 2169189 (Open Web Text)

Max Activating Token Index: 676

Text #6

Max Range: 4.8671. Min Range: -4.8671

Max Act: 4.5160. Min Act: -0.1700

Data Index: 1579413 (Open Web Text)

Max Activating Token Index: 628

Text #7

Max Range: 4.8671. Min Range: -4.8671

Max Act: 4.4915. Min Act: -0.1700

Data Index: 3100611 (Open Web Text)

Max Activating Token Index: 73

Text #8

Max Range: 4.8671. Min Range: -4.8671

Max Act: 4.4580. Min Act: -0.1700

Data Index: 3809883 (Open Web Text)

Max Activating Token Index: 513

Text #9

Max Range: 4.8671. Min Range: -4.8671

Max Act: 4.4078. Min Act: -0.1700

Data Index: 5469289 (Open Web Text)

Max Activating Token Index: 471

Text #10

Max Range: 4.8671. Min Range: -4.8671

Max Act: 4.4417. Min Act: -0.1700

Data Index: 8274012 (Open Web Text)

Max Activating Token Index: 823

Text #11

Max Range: 4.8671. Min Range: -4.8671

Max Act: 4.4180. Min Act: -0.1700

Data Index: 1346576 (Open Web Text)

Max Activating Token Index: 414

Text #12

Max Range: 4.8671. Min Range: -4.8671

Max Act: 4.4218. Min Act: -0.1700

Data Index: 4525179 (Open Web Text)

Max Activating Token Index: 608

Text #13

Max Range: 4.8671. Min Range: -4.8671

Max Act: 4.4181. Min Act: -0.1700

Data Index: 4178518 (Open Web Text)

Max Activating Token Index: 370

Text #14

Max Range: 4.8671. Min Range: -4.8671

Max Act: 4.4197. Min Act: -0.1700

Data Index: 559397 (Open Web Text)

Max Activating Token Index: 331

Text #15

Max Range: 4.8671. Min Range: -4.8671

Max Act: 4.3729. Min Act: -0.1700

Data Index: 4247195 (Open Web Text)

Max Activating Token Index: 719

Text #16

Max Range: 4.8671. Min Range: -4.8671

Max Act: 4.3476. Min Act: -0.1700

Data Index: 5054072 (Open Web Text)

Max Activating Token Index: 423

Text #17

Max Range: 4.8671. Min Range: -4.8671

Max Act: 4.4319. Min Act: -0.1700

Data Index: 2222896 (Open Web Text)

Max Activating Token Index: 460

Text #18

Max Range: 4.8671. Min Range: -4.8671

Max Act: 4.4123. Min Act: -0.1700

Data Index: 1601934 (Open Web Text)

Max Activating Token Index: 193

Text #19

Max Range: 4.8671. Min Range: -4.8671

Max Act: 4.3943. Min Act: -0.1700

Data Index: 7137530 (Open Web Text)

Max Activating Token Index: 322