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

Dataset: Open Web Text

Neuron 1720 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: 4.6870. Min Range: -4.6870

Max Act: 4.6870. Min Act: -0.1700

Data Index: 2541558 (Open Web Text)

Max Activating Token Index: 450

Text #1

Max Range: 4.6870. Min Range: -4.6870

Max Act: 4.6774. Min Act: -0.1700

Data Index: 7052654 (Open Web Text)

Max Activating Token Index: 503

Text #2

Max Range: 4.6870. Min Range: -4.6870

Max Act: 4.6233. Min Act: -0.1700

Data Index: 480326 (Open Web Text)

Max Activating Token Index: 571

Text #3

Max Range: 4.6870. Min Range: -4.6870

Max Act: 4.5560. Min Act: -0.1700

Data Index: 4181516 (Open Web Text)

Max Activating Token Index: 728

Text #4

Max Range: 4.6870. Min Range: -4.6870

Max Act: 4.5775. Min Act: -0.1700

Data Index: 5958617 (Open Web Text)

Max Activating Token Index: 447

Text #5

Max Range: 4.6870. Min Range: -4.6870

Max Act: 4.5451. Min Act: -0.1700

Data Index: 3943000 (Open Web Text)

Max Activating Token Index: 893

Text #6

Max Range: 4.6870. Min Range: -4.6870

Max Act: 4.5463. Min Act: -0.1700

Data Index: 1108489 (Open Web Text)

Max Activating Token Index: 102

Text #7

Max Range: 4.6870. Min Range: -4.6870

Max Act: 4.5535. Min Act: -0.1700

Data Index: 8535512 (Open Web Text)

Max Activating Token Index: 984

Text #8

Max Range: 4.6870. Min Range: -4.6870

Max Act: 4.4924. Min Act: -0.1700

Data Index: 7438688 (Open Web Text)

Max Activating Token Index: 867

Text #9

Max Range: 4.6870. Min Range: -4.6870

Max Act: 4.5419. Min Act: -0.1700

Data Index: 6676612 (Open Web Text)

Max Activating Token Index: 937

Text #10

Max Range: 4.6870. Min Range: -4.6870

Max Act: 4.4890. Min Act: -0.1700

Data Index: 7056830 (Open Web Text)

Max Activating Token Index: 776

Text #11

Max Range: 4.6870. Min Range: -4.6870

Max Act: 4.4817. Min Act: -0.1700

Data Index: 280202 (Open Web Text)

Max Activating Token Index: 345

Text #12

Max Range: 4.6870. Min Range: -4.6870

Max Act: 4.5065. Min Act: -0.1700

Data Index: 2708686 (Open Web Text)

Max Activating Token Index: 697

Text #13

Max Range: 4.6870. Min Range: -4.6870

Max Act: 4.4352. Min Act: -0.1700

Data Index: 2896113 (Open Web Text)

Max Activating Token Index: 88

Text #14

Max Range: 4.6870. Min Range: -4.6870

Max Act: 4.4402. Min Act: -0.1700

Data Index: 1209735 (Open Web Text)

Max Activating Token Index: 978

Text #15

Max Range: 4.6870. Min Range: -4.6870

Max Act: 4.4351. Min Act: -0.1700

Data Index: 6054099 (Open Web Text)

Max Activating Token Index: 488

Text #16

Max Range: 4.6870. Min Range: -4.6870

Max Act: 4.4799. Min Act: -0.1700

Data Index: 1616024 (Open Web Text)

Max Activating Token Index: 307

Text #17

Max Range: 4.6870. Min Range: -4.6870

Max Act: 4.4571. Min Act: -0.1700

Data Index: 7317055 (Open Web Text)

Max Activating Token Index: 273

Text #18

Max Range: 4.6870. Min Range: -4.6870

Max Act: 4.4124. Min Act: -0.1700

Data Index: 5243479 (Open Web Text)

Max Activating Token Index: 105

Text #19

Max Range: 4.6870. Min Range: -4.6870

Max Act: 4.4136. Min Act: -0.1700

Data Index: 7214683 (Open Web Text)

Max Activating Token Index: 447