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

Dataset: Open Web Text

Neuron 2431 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: 4.4662. Min Range: -4.4662

Max Act: 4.4660. Min Act: -0.1700

Data Index: 6279199 (Open Web Text)

Max Activating Token Index: 5

Text #1

Max Range: 4.4662. Min Range: -4.4662

Max Act: 4.4256. Min Act: -0.1700

Data Index: 6862781 (Open Web Text)

Max Activating Token Index: 208

Text #2

Max Range: 4.4662. Min Range: -4.4662

Max Act: 4.4484. Min Act: -0.1700

Data Index: 6545648 (Open Web Text)

Max Activating Token Index: 7

Text #3

Max Range: 4.4662. Min Range: -4.4662

Max Act: 4.4278. Min Act: -0.1700

Data Index: 3109745 (Open Web Text)

Max Activating Token Index: 488

Text #4

Max Range: 4.4662. Min Range: -4.4662

Max Act: 4.4530. Min Act: -0.1700

Data Index: 6452793 (Open Web Text)

Max Activating Token Index: 359

Text #5

Max Range: 4.4662. Min Range: -4.4662

Max Act: 4.4511. Min Act: -0.1700

Data Index: 2317759 (Open Web Text)

Max Activating Token Index: 85

Text #6

Max Range: 4.4662. Min Range: -4.4662

Max Act: 4.4344. Min Act: -0.1700

Data Index: 6136910 (Open Web Text)

Max Activating Token Index: 4

Text #7

Max Range: 4.4662. Min Range: -4.4662

Max Act: 4.4662. Min Act: -0.1700

Data Index: 5516986 (Open Web Text)

Max Activating Token Index: 635

Text #8

Max Range: 4.4662. Min Range: -4.4662

Max Act: 4.4209. Min Act: -0.1700

Data Index: 7276130 (Open Web Text)

Max Activating Token Index: 399

Text #9

Max Range: 4.4662. Min Range: -4.4662

Max Act: 4.4224. Min Act: -0.1700

Data Index: 4678573 (Open Web Text)

Max Activating Token Index: 136

Text #10

Max Range: 4.4662. Min Range: -4.4662

Max Act: 4.4461. Min Act: -0.1700

Data Index: 1188059 (Open Web Text)

Max Activating Token Index: 1012

Text #11

Max Range: 4.4662. Min Range: -4.4662

Max Act: 4.4263. Min Act: -0.1700

Data Index: 5532277 (Open Web Text)

Max Activating Token Index: 672

Text #12

Max Range: 4.4662. Min Range: -4.4662

Max Act: 4.4187. Min Act: -0.1700

Data Index: 5621622 (Open Web Text)

Max Activating Token Index: 617

Text #13

Max Range: 4.4662. Min Range: -4.4662

Max Act: 4.3849. Min Act: -0.1700

Data Index: 2776018 (Open Web Text)

Max Activating Token Index: 14

Text #14

Max Range: 4.4662. Min Range: -4.4662

Max Act: 4.4044. Min Act: -0.1700

Data Index: 1065945 (Open Web Text)

Max Activating Token Index: 296

Text #15

Max Range: 4.4662. Min Range: -4.4662

Max Act: 4.3864. Min Act: -0.1700

Data Index: 5119779 (Open Web Text)

Max Activating Token Index: 952

Text #16

Max Range: 4.4662. Min Range: -4.4662

Max Act: 4.3750. Min Act: -0.1700

Data Index: 6210176 (Open Web Text)

Max Activating Token Index: 563

Text #17

Max Range: 4.4662. Min Range: -4.4662

Max Act: 4.4083. Min Act: -0.1700

Data Index: 4681269 (Open Web Text)

Max Activating Token Index: 237

Text #18

Max Range: 4.4662. Min Range: -4.4662

Max Act: 4.3849. Min Act: -0.1700

Data Index: 6452792 (Open Web Text)

Max Activating Token Index: 903

Text #19

Max Range: 4.4662. Min Range: -4.4662

Max Act: 4.4115. Min Act: -0.1700

Data Index: 633826 (Open Web Text)

Max Activating Token Index: 798