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

Dataset: Open Web Text

Neuron 1226 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: 3.9597. Min Range: -3.9597

Max Act: 3.9597. Min Act: -0.1700

Data Index: 1643567 (Open Web Text)

Max Activating Token Index: 504

Text #1

Max Range: 3.9597. Min Range: -3.9597

Max Act: 3.9337. Min Act: -0.1700

Data Index: 5580377 (Open Web Text)

Max Activating Token Index: 952

Text #2

Max Range: 3.9597. Min Range: -3.9597

Max Act: 3.9264. Min Act: -0.1700

Data Index: 5436509 (Open Web Text)

Max Activating Token Index: 580

Text #3

Max Range: 3.9597. Min Range: -3.9597

Max Act: 3.9237. Min Act: -0.1700

Data Index: 2059060 (Open Web Text)

Max Activating Token Index: 326

Text #4

Max Range: 3.9597. Min Range: -3.9597

Max Act: 3.9532. Min Act: -0.1700

Data Index: 4418443 (Open Web Text)

Max Activating Token Index: 453

Text #5

Max Range: 3.9597. Min Range: -3.9597

Max Act: 3.9456. Min Act: -0.1700

Data Index: 8253986 (Open Web Text)

Max Activating Token Index: 790

Text #6

Max Range: 3.9597. Min Range: -3.9597

Max Act: 3.8947. Min Act: -0.1700

Data Index: 6871527 (Open Web Text)

Max Activating Token Index: 731

Text #7

Max Range: 3.9597. Min Range: -3.9597

Max Act: 3.9051. Min Act: -0.1700

Data Index: 6232529 (Open Web Text)

Max Activating Token Index: 393

Text #8

Max Range: 3.9597. Min Range: -3.9597

Max Act: 3.8889. Min Act: -0.1700

Data Index: 8534665 (Open Web Text)

Max Activating Token Index: 770

Text #9

Max Range: 3.9597. Min Range: -3.9597

Max Act: 3.8954. Min Act: -0.1700

Data Index: 2811458 (Open Web Text)

Max Activating Token Index: 505

Text #10

Max Range: 3.9597. Min Range: -3.9597

Max Act: 3.8775. Min Act: -0.1700

Data Index: 7999174 (Open Web Text)

Max Activating Token Index: 537

Text #11

Max Range: 3.9597. Min Range: -3.9597

Max Act: 3.8706. Min Act: -0.1700

Data Index: 8022415 (Open Web Text)

Max Activating Token Index: 406

Text #12

Max Range: 3.9597. Min Range: -3.9597

Max Act: 3.8755. Min Act: -0.1700

Data Index: 6099732 (Open Web Text)

Max Activating Token Index: 538

Text #13

Max Range: 3.9597. Min Range: -3.9597

Max Act: 3.8839. Min Act: -0.1700

Data Index: 4982022 (Open Web Text)

Max Activating Token Index: 147

Text #14

Max Range: 3.9597. Min Range: -3.9597

Max Act: 3.8712. Min Act: -0.1700

Data Index: 8723508 (Open Web Text)

Max Activating Token Index: 378

Text #15

Max Range: 3.9597. Min Range: -3.9597

Max Act: 3.8732. Min Act: -0.1700

Data Index: 1179117 (Open Web Text)

Max Activating Token Index: 637

Text #16

Max Range: 3.9597. Min Range: -3.9597

Max Act: 3.8661. Min Act: -0.1700

Data Index: 5514116 (Open Web Text)

Max Activating Token Index: 214

Text #17

Max Range: 3.9597. Min Range: -3.9597

Max Act: 3.8359. Min Act: -0.1700

Data Index: 5114645 (Open Web Text)

Max Activating Token Index: 648

Text #18

Max Range: 3.9597. Min Range: -3.9597

Max Act: 3.8612. Min Act: -0.1700

Data Index: 5229520 (Open Web Text)

Max Activating Token Index: 501

Text #19

Max Range: 3.9597. Min Range: -3.9597

Max Act: 3.8539. Min Act: -0.1700

Data Index: 754925 (Open Web Text)

Max Activating Token Index: 419