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

Dataset: Open Web Text

Neuron 2611 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: 4.7909. Min Range: -4.7909

Max Act: 4.7909. Min Act: -0.1700

Data Index: 4066198 (Open Web Text)

Max Activating Token Index: 530

Text #1

Max Range: 4.7909. Min Range: -4.7909

Max Act: 4.7202. Min Act: -0.1700

Data Index: 5067613 (Open Web Text)

Max Activating Token Index: 999

Text #2

Max Range: 4.7909. Min Range: -4.7909

Max Act: 4.7211. Min Act: -0.1700

Data Index: 6558556 (Open Web Text)

Max Activating Token Index: 454

Text #3

Max Range: 4.7909. Min Range: -4.7909

Max Act: 4.7221. Min Act: -0.1700

Data Index: 6806806 (Open Web Text)

Max Activating Token Index: 555

Text #4

Max Range: 4.7909. Min Range: -4.7909

Max Act: 4.6478. Min Act: -0.1700

Data Index: 1289578 (Open Web Text)

Max Activating Token Index: 565

Text #5

Max Range: 4.7909. Min Range: -4.7909

Max Act: 4.6475. Min Act: -0.1700

Data Index: 8813780 (Open Web Text)

Max Activating Token Index: 651

Text #6

Max Range: 4.7909. Min Range: -4.7909

Max Act: 4.6730. Min Act: -0.1700

Data Index: 5798793 (Open Web Text)

Max Activating Token Index: 981

Text #7

Max Range: 4.7909. Min Range: -4.7909

Max Act: 4.6786. Min Act: -0.1698

Data Index: 2315394 (Open Web Text)

Max Activating Token Index: 740

Text #8

Max Range: 4.7909. Min Range: -4.7909

Max Act: 4.6517. Min Act: -0.1700

Data Index: 6126744 (Open Web Text)

Max Activating Token Index: 812

Text #9

Max Range: 4.7909. Min Range: -4.7909

Max Act: 4.6438. Min Act: -0.1700

Data Index: 2404982 (Open Web Text)

Max Activating Token Index: 479

Text #10

Max Range: 4.7909. Min Range: -4.7909

Max Act: 4.5854. Min Act: -0.1700

Data Index: 6851358 (Open Web Text)

Max Activating Token Index: 641

Text #11

Max Range: 4.7909. Min Range: -4.7909

Max Act: 4.6320. Min Act: -0.1700

Data Index: 1518163 (Open Web Text)

Max Activating Token Index: 701

Text #12

Max Range: 4.7909. Min Range: -4.7909

Max Act: 4.6428. Min Act: -0.1700

Data Index: 2068524 (Open Web Text)

Max Activating Token Index: 505

Text #13

Max Range: 4.7909. Min Range: -4.7909

Max Act: 4.5964. Min Act: -0.1700

Data Index: 5405047 (Open Web Text)

Max Activating Token Index: 445

Text #14

Max Range: 4.7909. Min Range: -4.7909

Max Act: 4.6230. Min Act: -0.1700

Data Index: 1199141 (Open Web Text)

Max Activating Token Index: 549

Text #15

Max Range: 4.7909. Min Range: -4.7909

Max Act: 4.5961. Min Act: -0.1700

Data Index: 2791335 (Open Web Text)

Max Activating Token Index: 608

Text #16

Max Range: 4.7909. Min Range: -4.7909

Max Act: 4.5897. Min Act: -0.1700

Data Index: 8044741 (Open Web Text)

Max Activating Token Index: 726

Text #17

Max Range: 4.7909. Min Range: -4.7909

Max Act: 4.5787. Min Act: -0.1700

Data Index: 5391344 (Open Web Text)

Max Activating Token Index: 22

Text #18

Max Range: 4.7909. Min Range: -4.7909

Max Act: 4.6141. Min Act: -0.1700

Data Index: 3971950 (Open Web Text)

Max Activating Token Index: 177

Text #19

Max Range: 4.7909. Min Range: -4.7909

Max Act: 4.5202. Min Act: -0.1700

Data Index: 93630 (Open Web Text)

Max Activating Token Index: 968