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

Dataset: Open Web Text

Neuron 1991 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: 4.8995. Min Range: -4.8995

Max Act: 4.8995. Min Act: -0.1700

Data Index: 364448 (Open Web Text)

Max Activating Token Index: 1012

Text #1

Max Range: 4.8995. Min Range: -4.8995

Max Act: 4.8496. Min Act: -0.1700

Data Index: 8526176 (Open Web Text)

Max Activating Token Index: 234

Text #2

Max Range: 4.8995. Min Range: -4.8995

Max Act: 4.6197. Min Act: -0.1700

Data Index: 1180924 (Open Web Text)

Max Activating Token Index: 253

Text #3

Max Range: 4.8995. Min Range: -4.8995

Max Act: 4.5824. Min Act: -0.1700

Data Index: 7412068 (Open Web Text)

Max Activating Token Index: 157

Text #4

Max Range: 4.8995. Min Range: -4.8995

Max Act: 4.5941. Min Act: -0.1700

Data Index: 3747835 (Open Web Text)

Max Activating Token Index: 913

Text #5

Max Range: 4.8995. Min Range: -4.8995

Max Act: 4.5757. Min Act: -0.1700

Data Index: 1049700 (Open Web Text)

Max Activating Token Index: 911

Text #6

Max Range: 4.8995. Min Range: -4.8995

Max Act: 4.5453. Min Act: -0.1700

Data Index: 3612746 (Open Web Text)

Max Activating Token Index: 558

Text #7

Max Range: 4.8995. Min Range: -4.8995

Max Act: 4.5366. Min Act: -0.1700

Data Index: 3940686 (Open Web Text)

Max Activating Token Index: 361

Text #8

Max Range: 4.8995. Min Range: -4.8995

Max Act: 4.4970. Min Act: -0.1700

Data Index: 8099698 (Open Web Text)

Max Activating Token Index: 612

Text #9

Max Range: 4.8995. Min Range: -4.8995

Max Act: 4.4771. Min Act: -0.1700

Data Index: 7568391 (Open Web Text)

Max Activating Token Index: 259

Text #10

Max Range: 4.8995. Min Range: -4.8995

Max Act: 4.4300. Min Act: -0.1700

Data Index: 4215216 (Open Web Text)

Max Activating Token Index: 1017

Text #11

Max Range: 4.8995. Min Range: -4.8995

Max Act: 4.4336. Min Act: -0.1700

Data Index: 8751161 (Open Web Text)

Max Activating Token Index: 958

Text #12

Max Range: 4.8995. Min Range: -4.8995

Max Act: 4.4465. Min Act: -0.1700

Data Index: 2045638 (Open Web Text)

Max Activating Token Index: 901

Text #13

Max Range: 4.8995. Min Range: -4.8995

Max Act: 4.4469. Min Act: -0.1700

Data Index: 2430587 (Open Web Text)

Max Activating Token Index: 696

Text #14

Max Range: 4.8995. Min Range: -4.8995

Max Act: 4.4587. Min Act: -0.1700

Data Index: 3000132 (Open Web Text)

Max Activating Token Index: 376

Text #15

Max Range: 4.8995. Min Range: -4.8995

Max Act: 4.4397. Min Act: -0.1700

Data Index: 7162965 (Open Web Text)

Max Activating Token Index: 529

Text #16

Max Range: 4.8995. Min Range: -4.8995

Max Act: 4.4254. Min Act: -0.1700

Data Index: 3181976 (Open Web Text)

Max Activating Token Index: 677

Text #17

Max Range: 4.8995. Min Range: -4.8995

Max Act: 4.3959. Min Act: -0.1700

Data Index: 7591855 (Open Web Text)

Max Activating Token Index: 591

Text #18

Max Range: 4.8995. Min Range: -4.8995

Max Act: 4.4228. Min Act: -0.1700

Data Index: 3955476 (Open Web Text)

Max Activating Token Index: 687

Text #19

Max Range: 4.8995. Min Range: -4.8995

Max Act: 4.3998. Min Act: -0.1700

Data Index: 2049854 (Open Web Text)

Max Activating Token Index: 553