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

Dataset: Open Web Text

Neuron 2276 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: 5.0000. Min Range: -5.0000

Max Act: 4.9712. Min Act: -0.1700

Data Index: 5843710 (Open Web Text)

Max Activating Token Index: 942

Text #1

Max Range: 5.0000. Min Range: -5.0000

Max Act: 5.0000. Min Act: -0.1700

Data Index: 4686131 (Open Web Text)

Max Activating Token Index: 454

Text #2

Max Range: 5.0000. Min Range: -5.0000

Max Act: 4.9539. Min Act: -0.1700

Data Index: 3138444 (Open Web Text)

Max Activating Token Index: 417

Text #3

Max Range: 5.0000. Min Range: -5.0000

Max Act: 4.9872. Min Act: -0.1700

Data Index: 7283736 (Open Web Text)

Max Activating Token Index: 75

Text #4

Max Range: 5.0000. Min Range: -5.0000

Max Act: 4.9445. Min Act: -0.1700

Data Index: 5167013 (Open Web Text)

Max Activating Token Index: 512

Text #5

Max Range: 5.0000. Min Range: -5.0000

Max Act: 4.8931. Min Act: -0.1699

Data Index: 4606852 (Open Web Text)

Max Activating Token Index: 516

Text #6

Max Range: 5.0000. Min Range: -5.0000

Max Act: 4.9266. Min Act: -0.1700

Data Index: 3128425 (Open Web Text)

Max Activating Token Index: 168

Text #7

Max Range: 5.0000. Min Range: -5.0000

Max Act: 4.9208. Min Act: -0.1700

Data Index: 5446754 (Open Web Text)

Max Activating Token Index: 27

Text #8

Max Range: 5.0000. Min Range: -5.0000

Max Act: 4.9082. Min Act: -0.1700

Data Index: 5104440 (Open Web Text)

Max Activating Token Index: 215

Text #9

Max Range: 5.0000. Min Range: -5.0000

Max Act: 4.8948. Min Act: -0.1700

Data Index: 517551 (Open Web Text)

Max Activating Token Index: 416

Text #10

Max Range: 5.0000. Min Range: -5.0000

Max Act: 4.9056. Min Act: -0.1700

Data Index: 3138441 (Open Web Text)

Max Activating Token Index: 121

Text #11

Max Range: 5.0000. Min Range: -5.0000

Max Act: 4.9299. Min Act: -0.1700

Data Index: 7208159 (Open Web Text)

Max Activating Token Index: 381

Text #12

Max Range: 5.0000. Min Range: -5.0000

Max Act: 4.8401. Min Act: -0.1700

Data Index: 6332590 (Open Web Text)

Max Activating Token Index: 406

Text #13

Max Range: 5.0000. Min Range: -5.0000

Max Act: 4.8644. Min Act: -0.1700

Data Index: 4924911 (Open Web Text)

Max Activating Token Index: 535

Text #14

Max Range: 5.0000. Min Range: -5.0000

Max Act: 4.8626. Min Act: -0.1700

Data Index: 555572 (Open Web Text)

Max Activating Token Index: 22

Text #15

Max Range: 5.0000. Min Range: -5.0000

Max Act: 4.8430. Min Act: -0.1700

Data Index: 1031562 (Open Web Text)

Max Activating Token Index: 463

Text #16

Max Range: 5.0000. Min Range: -5.0000

Max Act: 4.8936. Min Act: -0.1700

Data Index: 252064 (Open Web Text)

Max Activating Token Index: 831

Text #17

Max Range: 5.0000. Min Range: -5.0000

Max Act: 4.9086. Min Act: -0.1700

Data Index: 2387968 (Open Web Text)

Max Activating Token Index: 601

Text #18

Max Range: 5.0000. Min Range: -5.0000

Max Act: 4.8076. Min Act: -0.1700

Data Index: 6920714 (Open Web Text)

Max Activating Token Index: 974

Text #19

Max Range: 5.0000. Min Range: -5.0000

Max Act: 4.8348. Min Act: -0.1700

Data Index: 555566 (Open Web Text)

Max Activating Token Index: 21