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

Dataset: Open Web Text

Neuron 1642 in Layer 1

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: 1.6771. Min Range: -1.6771

Max Act: 1.6771. Min Act: -0.1700

Data Index: 21462 (Open Web Text)

Max Activating Token Index: 512

Text #1

Max Range: 1.6771. Min Range: -1.6771

Max Act: 1.6640. Min Act: -0.1700

Data Index: 2183075 (Open Web Text)

Max Activating Token Index: 36

Text #2

Max Range: 1.6771. Min Range: -1.6771

Max Act: 1.6603. Min Act: -0.1700

Data Index: 5267614 (Open Web Text)

Max Activating Token Index: 153

Text #3

Max Range: 1.6771. Min Range: -1.6771

Max Act: 1.6505. Min Act: -0.1700

Data Index: 4519795 (Open Web Text)

Max Activating Token Index: 443

Text #4

Max Range: 1.6771. Min Range: -1.6771

Max Act: 1.6513. Min Act: -0.1700

Data Index: 160225 (Open Web Text)

Max Activating Token Index: 301

Text #5

Max Range: 1.6771. Min Range: -1.6771

Max Act: 1.6598. Min Act: -0.1700

Data Index: 3224278 (Open Web Text)

Max Activating Token Index: 806

Text #6

Max Range: 1.6771. Min Range: -1.6771

Max Act: 1.6525. Min Act: -0.1700

Data Index: 5386128 (Open Web Text)

Max Activating Token Index: 295

Text #7

Max Range: 1.6771. Min Range: -1.6771

Max Act: 1.6563. Min Act: -0.1700

Data Index: 2848599 (Open Web Text)

Max Activating Token Index: 735

Text #8

Max Range: 1.6771. Min Range: -1.6771

Max Act: 1.6417. Min Act: -0.1700

Data Index: 127833 (Open Web Text)

Max Activating Token Index: 490

Text #9

Max Range: 1.6771. Min Range: -1.6771

Max Act: 1.6352. Min Act: -0.1700

Data Index: 5228332 (Open Web Text)

Max Activating Token Index: 568

Text #10

Max Range: 1.6771. Min Range: -1.6771

Max Act: 1.6460. Min Act: -0.1700

Data Index: 359903 (Open Web Text)

Max Activating Token Index: 283

Text #11

Max Range: 1.6771. Min Range: -1.6771

Max Act: 1.6293. Min Act: -0.1700

Data Index: 5188043 (Open Web Text)

Max Activating Token Index: 292

Text #12

Max Range: 1.6771. Min Range: -1.6771

Max Act: 1.6243. Min Act: -0.1700

Data Index: 4224929 (Open Web Text)

Max Activating Token Index: 715

Text #13

Max Range: 1.6771. Min Range: -1.6771

Max Act: 1.6245. Min Act: -0.1700

Data Index: 4849713 (Open Web Text)

Max Activating Token Index: 415

Text #14

Max Range: 1.6771. Min Range: -1.6771

Max Act: 1.6208. Min Act: -0.1700

Data Index: 2599638 (Open Web Text)

Max Activating Token Index: 371

Text #15

Max Range: 1.6771. Min Range: -1.6771

Max Act: 1.6224. Min Act: -0.1700

Data Index: 3741902 (Open Web Text)

Max Activating Token Index: 830

Text #16

Max Range: 1.6771. Min Range: -1.6771

Max Act: 1.6216. Min Act: -0.1700

Data Index: 788443 (Open Web Text)

Max Activating Token Index: 626

Text #17

Max Range: 1.6771. Min Range: -1.6771

Max Act: 1.6068. Min Act: -0.1700

Data Index: 5107296 (Open Web Text)

Max Activating Token Index: 979

Text #18

Max Range: 1.6771. Min Range: -1.6771

Max Act: 1.6151. Min Act: -0.1700

Data Index: 3210368 (Open Web Text)

Max Activating Token Index: 1022

Text #19

Max Range: 1.6771. Min Range: -1.6771

Max Act: 1.6105. Min Act: -0.1700

Data Index: 3675339 (Open Web Text)

Max Activating Token Index: 404