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

Dataset: Open Web Text

Neuron 47 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: 5.6770. Min Range: -5.6770

Max Act: 5.6770. Min Act: -0.1700

Data Index: 4848935 (Open Web Text)

Max Activating Token Index: 338

Text #1

Max Range: 5.6770. Min Range: -5.6770

Max Act: 5.6277. Min Act: -0.1700

Data Index: 7769832 (Open Web Text)

Max Activating Token Index: 431

Text #2

Max Range: 5.6770. Min Range: -5.6770

Max Act: 5.6014. Min Act: -0.1700

Data Index: 2150314 (Open Web Text)

Max Activating Token Index: 748

Text #3

Max Range: 5.6770. Min Range: -5.6770

Max Act: 5.5713. Min Act: -0.1700

Data Index: 6873345 (Open Web Text)

Max Activating Token Index: 582

Text #4

Max Range: 5.6770. Min Range: -5.6770

Max Act: 5.5715. Min Act: -0.1700

Data Index: 4335113 (Open Web Text)

Max Activating Token Index: 367

Text #5

Max Range: 5.6770. Min Range: -5.6770

Max Act: 5.5499. Min Act: -0.1700

Data Index: 4076792 (Open Web Text)

Max Activating Token Index: 336

Text #6

Max Range: 5.6770. Min Range: -5.6770

Max Act: 5.5782. Min Act: -0.1700

Data Index: 1364528 (Open Web Text)

Max Activating Token Index: 237

Text #7

Max Range: 5.6770. Min Range: -5.6770

Max Act: 5.5423. Min Act: -0.1700

Data Index: 6544447 (Open Web Text)

Max Activating Token Index: 254

Text #8

Max Range: 5.6770. Min Range: -5.6770

Max Act: 5.4917. Min Act: -0.1700

Data Index: 6361222 (Open Web Text)

Max Activating Token Index: 781

Text #9

Max Range: 5.6770. Min Range: -5.6770

Max Act: 5.5117. Min Act: -0.1700

Data Index: 3368929 (Open Web Text)

Max Activating Token Index: 323

Text #10

Max Range: 5.6770. Min Range: -5.6770

Max Act: 5.4468. Min Act: -0.1700

Data Index: 6318057 (Open Web Text)

Max Activating Token Index: 714

Text #11

Max Range: 5.6770. Min Range: -5.6770

Max Act: 5.4775. Min Act: -0.1700

Data Index: 2020076 (Open Web Text)

Max Activating Token Index: 478

Text #12

Max Range: 5.6770. Min Range: -5.6770

Max Act: 5.4344. Min Act: -0.1700

Data Index: 4984641 (Open Web Text)

Max Activating Token Index: 422

Text #13

Max Range: 5.6770. Min Range: -5.6770

Max Act: 5.4284. Min Act: -0.1700

Data Index: 6030250 (Open Web Text)

Max Activating Token Index: 668

Text #14

Max Range: 5.6770. Min Range: -5.6770

Max Act: 5.3861. Min Act: -0.1700

Data Index: 890180 (Open Web Text)

Max Activating Token Index: 159

Text #15

Max Range: 5.6770. Min Range: -5.6770

Max Act: 5.4098. Min Act: -0.1700

Data Index: 778370 (Open Web Text)

Max Activating Token Index: 433

Text #16

Max Range: 5.6770. Min Range: -5.6770

Max Act: 5.4103. Min Act: -0.1700

Data Index: 1333696 (Open Web Text)

Max Activating Token Index: 668

Text #17

Max Range: 5.6770. Min Range: -5.6770

Max Act: 5.4144. Min Act: -0.1700

Data Index: 997313 (Open Web Text)

Max Activating Token Index: 928

Text #18

Max Range: 5.6770. Min Range: -5.6770

Max Act: 5.3893. Min Act: -0.1700

Data Index: 8041654 (Open Web Text)

Max Activating Token Index: 525

Text #19

Max Range: 5.6770. Min Range: -5.6770

Max Act: 5.3876. Min Act: -0.1700

Data Index: 8698374 (Open Web Text)

Max Activating Token Index: 405