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

Dataset: Open Web Text

Neuron 786 in Layer 4

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: 3.6204. Min Range: -3.6204

Max Act: 3.6204. Min Act: -0.1700

Data Index: 5792122 (Open Web Text)

Max Activating Token Index: 676

Text #1

Max Range: 3.6204. Min Range: -3.6204

Max Act: 3.5277. Min Act: -0.1700

Data Index: 6720867 (Open Web Text)

Max Activating Token Index: 666

Text #2

Max Range: 3.6204. Min Range: -3.6204

Max Act: 3.5089. Min Act: -0.1700

Data Index: 1190575 (Open Web Text)

Max Activating Token Index: 656

Text #3

Max Range: 3.6204. Min Range: -3.6204

Max Act: 3.4559. Min Act: -0.1700

Data Index: 7426446 (Open Web Text)

Max Activating Token Index: 373

Text #4

Max Range: 3.6204. Min Range: -3.6204

Max Act: 3.4834. Min Act: -0.1700

Data Index: 103836 (Open Web Text)

Max Activating Token Index: 164

Text #5

Max Range: 3.6204. Min Range: -3.6204

Max Act: 3.4527. Min Act: -0.1700

Data Index: 1875023 (Open Web Text)

Max Activating Token Index: 993

Text #6

Max Range: 3.6204. Min Range: -3.6204

Max Act: 3.4528. Min Act: -0.1700

Data Index: 6771420 (Open Web Text)

Max Activating Token Index: 57

Text #7

Max Range: 3.6204. Min Range: -3.6204

Max Act: 3.4436. Min Act: -0.1700

Data Index: 4425768 (Open Web Text)

Max Activating Token Index: 580

Text #8

Max Range: 3.6204. Min Range: -3.6204

Max Act: 3.4446. Min Act: -0.1700

Data Index: 4147155 (Open Web Text)

Max Activating Token Index: 331

Text #9

Max Range: 3.6204. Min Range: -3.6204

Max Act: 3.4215. Min Act: -0.1700

Data Index: 4820119 (Open Web Text)

Max Activating Token Index: 514

Text #10

Max Range: 3.6204. Min Range: -3.6204

Max Act: 3.4494. Min Act: -0.1700

Data Index: 1861436 (Open Web Text)

Max Activating Token Index: 591

Text #11

Max Range: 3.6204. Min Range: -3.6204

Max Act: 3.4039. Min Act: -0.1700

Data Index: 2125719 (Open Web Text)

Max Activating Token Index: 404

Text #12

Max Range: 3.6204. Min Range: -3.6204

Max Act: 3.3915. Min Act: -0.1700

Data Index: 5148729 (Open Web Text)

Max Activating Token Index: 275

Text #13

Max Range: 3.6204. Min Range: -3.6204

Max Act: 3.3863. Min Act: -0.1700

Data Index: 7562779 (Open Web Text)

Max Activating Token Index: 736

Text #14

Max Range: 3.6204. Min Range: -3.6204

Max Act: 3.4032. Min Act: -0.1700

Data Index: 5114297 (Open Web Text)

Max Activating Token Index: 211

Text #15

Max Range: 3.6204. Min Range: -3.6204

Max Act: 3.3882. Min Act: -0.1700

Data Index: 3431171 (Open Web Text)

Max Activating Token Index: 449

Text #16

Max Range: 3.6204. Min Range: -3.6204

Max Act: 3.3828. Min Act: -0.1700

Data Index: 7366392 (Open Web Text)

Max Activating Token Index: 144

Text #17

Max Range: 3.6204. Min Range: -3.6204

Max Act: 3.3985. Min Act: -0.1700

Data Index: 548422 (Open Web Text)

Max Activating Token Index: 700

Text #18

Max Range: 3.6204. Min Range: -3.6204

Max Act: 3.3896. Min Act: -0.1700

Data Index: 3909180 (Open Web Text)

Max Activating Token Index: 365

Text #19

Max Range: 3.6204. Min Range: -3.6204

Max Act: 3.3712. Min Act: -0.1700

Data Index: 2013477 (Open Web Text)

Max Activating Token Index: 528