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

Dataset: Open Web Text

Neuron 2786 in Layer 2

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: 3.9445. Min Range: -3.9445

Max Act: 3.9445. Min Act: -0.1700

Data Index: 2831286 (Open Web Text)

Max Activating Token Index: 69

Text #1

Max Range: 3.9445. Min Range: -3.9445

Max Act: 3.9344. Min Act: -0.1700

Data Index: 5354757 (Open Web Text)

Max Activating Token Index: 477

Text #2

Max Range: 3.9445. Min Range: -3.9445

Max Act: 3.9167. Min Act: -0.1700

Data Index: 1458307 (Open Web Text)

Max Activating Token Index: 24

Text #3

Max Range: 3.9445. Min Range: -3.9445

Max Act: 3.8776. Min Act: -0.1700

Data Index: 2288131 (Open Web Text)

Max Activating Token Index: 549

Text #4

Max Range: 3.9445. Min Range: -3.9445

Max Act: 3.8979. Min Act: -0.1700

Data Index: 1815385 (Open Web Text)

Max Activating Token Index: 466

Text #5

Max Range: 3.9445. Min Range: -3.9445

Max Act: 3.8577. Min Act: -0.1700

Data Index: 5138649 (Open Web Text)

Max Activating Token Index: 362

Text #6

Max Range: 3.9445. Min Range: -3.9445

Max Act: 3.8546. Min Act: -0.1700

Data Index: 6298503 (Open Web Text)

Max Activating Token Index: 469

Text #7

Max Range: 3.9445. Min Range: -3.9445

Max Act: 3.8453. Min Act: -0.1700

Data Index: 816526 (Open Web Text)

Max Activating Token Index: 718

Text #8

Max Range: 3.9445. Min Range: -3.9445

Max Act: 3.8029. Min Act: -0.1700

Data Index: 7944043 (Open Web Text)

Max Activating Token Index: 351

Text #9

Max Range: 3.9445. Min Range: -3.9445

Max Act: 3.8336. Min Act: -0.1700

Data Index: 1836011 (Open Web Text)

Max Activating Token Index: 896

Text #10

Max Range: 3.9445. Min Range: -3.9445

Max Act: 3.8027. Min Act: -0.1700

Data Index: 7916412 (Open Web Text)

Max Activating Token Index: 802

Text #11

Max Range: 3.9445. Min Range: -3.9445

Max Act: 3.8193. Min Act: -0.1700

Data Index: 3872777 (Open Web Text)

Max Activating Token Index: 960

Text #12

Max Range: 3.9445. Min Range: -3.9445

Max Act: 3.7887. Min Act: -0.1700

Data Index: 3441227 (Open Web Text)

Max Activating Token Index: 636

Text #13

Max Range: 3.9445. Min Range: -3.9445

Max Act: 3.8046. Min Act: -0.1700

Data Index: 1076606 (Open Web Text)

Max Activating Token Index: 554

Text #14

Max Range: 3.9445. Min Range: -3.9445

Max Act: 3.7869. Min Act: -0.1700

Data Index: 3912868 (Open Web Text)

Max Activating Token Index: 118

Text #15

Max Range: 3.9445. Min Range: -3.9445

Max Act: 3.7926. Min Act: -0.1700

Data Index: 3290985 (Open Web Text)

Max Activating Token Index: 683

Text #16

Max Range: 3.9445. Min Range: -3.9445

Max Act: 3.7423. Min Act: -0.1700

Data Index: 3072693 (Open Web Text)

Max Activating Token Index: 863

Text #17

Max Range: 3.9445. Min Range: -3.9445

Max Act: 3.7408. Min Act: -0.1700

Data Index: 6911294 (Open Web Text)

Max Activating Token Index: 525

Text #18

Max Range: 3.9445. Min Range: -3.9445

Max Act: 3.7437. Min Act: -0.1700

Data Index: 6256993 (Open Web Text)

Max Activating Token Index: 370

Text #19

Max Range: 3.9445. Min Range: -3.9445

Max Act: 3.7759. Min Act: -0.1700

Data Index: 2588977 (Open Web Text)

Max Activating Token Index: 581