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

Dataset: Open Web Text

Neuron 828 in Layer 3

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: 4.4642. Min Range: -4.4642

Max Act: 4.4642. Min Act: -0.1700

Data Index: 1816914 (Open Web Text)

Max Activating Token Index: 425

Text #1

Max Range: 4.4642. Min Range: -4.4642

Max Act: 4.3528. Min Act: -0.1700

Data Index: 6954165 (Open Web Text)

Max Activating Token Index: 1019

Text #2

Max Range: 4.4642. Min Range: -4.4642

Max Act: 4.2493. Min Act: -0.1700

Data Index: 8147227 (Open Web Text)

Max Activating Token Index: 637

Text #3

Max Range: 4.4642. Min Range: -4.4642

Max Act: 4.2243. Min Act: -0.1700

Data Index: 7044716 (Open Web Text)

Max Activating Token Index: 951

Text #4

Max Range: 4.4642. Min Range: -4.4642

Max Act: 4.1732. Min Act: -0.1700

Data Index: 4189590 (Open Web Text)

Max Activating Token Index: 647

Text #5

Max Range: 4.4642. Min Range: -4.4642

Max Act: 4.1694. Min Act: -0.1700

Data Index: 5783822 (Open Web Text)

Max Activating Token Index: 569

Text #6

Max Range: 4.4642. Min Range: -4.4642

Max Act: 4.1604. Min Act: -0.1700

Data Index: 3958967 (Open Web Text)

Max Activating Token Index: 235

Text #7

Max Range: 4.4642. Min Range: -4.4642

Max Act: 4.1486. Min Act: -0.1700

Data Index: 8559129 (Open Web Text)

Max Activating Token Index: 405

Text #8

Max Range: 4.4642. Min Range: -4.4642

Max Act: 4.1473. Min Act: -0.1700

Data Index: 4178632 (Open Web Text)

Max Activating Token Index: 525

Text #9

Max Range: 4.4642. Min Range: -4.4642

Max Act: 4.1221. Min Act: -0.1700

Data Index: 8551724 (Open Web Text)

Max Activating Token Index: 247

Text #10

Max Range: 4.4642. Min Range: -4.4642

Max Act: 4.1540. Min Act: -0.1700

Data Index: 3235019 (Open Web Text)

Max Activating Token Index: 612

Text #11

Max Range: 4.4642. Min Range: -4.4642

Max Act: 4.1492. Min Act: -0.1700

Data Index: 426864 (Open Web Text)

Max Activating Token Index: 320

Text #12

Max Range: 4.4642. Min Range: -4.4642

Max Act: 4.1228. Min Act: -0.1700

Data Index: 5924723 (Open Web Text)

Max Activating Token Index: 1015

Text #13

Max Range: 4.4642. Min Range: -4.4642

Max Act: 4.1474. Min Act: -0.1700

Data Index: 3604685 (Open Web Text)

Max Activating Token Index: 846

Text #14

Max Range: 4.4642. Min Range: -4.4642

Max Act: 4.1076. Min Act: -0.1700

Data Index: 4476247 (Open Web Text)

Max Activating Token Index: 131

Text #15

Max Range: 4.4642. Min Range: -4.4642

Max Act: 4.0958. Min Act: -0.1700

Data Index: 5700301 (Open Web Text)

Max Activating Token Index: 409

Text #16

Max Range: 4.4642. Min Range: -4.4642

Max Act: 4.0977. Min Act: -0.1700

Data Index: 7426062 (Open Web Text)

Max Activating Token Index: 724

Text #17

Max Range: 4.4642. Min Range: -4.4642

Max Act: 4.0484. Min Act: -0.1700

Data Index: 4821598 (Open Web Text)

Max Activating Token Index: 999

Text #18

Max Range: 4.4642. Min Range: -4.4642

Max Act: 4.0574. Min Act: -0.1700

Data Index: 3267302 (Open Web Text)

Max Activating Token Index: 761

Text #19

Max Range: 4.4642. Min Range: -4.4642

Max Act: 4.0652. Min Act: -0.1700

Data Index: 7723050 (Open Web Text)

Max Activating Token Index: 384