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

Dataset: Open Web Text

Neuron 2174 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: 3.1736. Min Range: -3.1736

Max Act: 3.1736. Min Act: -0.1700

Data Index: 6633608 (Open Web Text)

Max Activating Token Index: 416

Text #1

Max Range: 3.1736. Min Range: -3.1736

Max Act: 3.0973. Min Act: -0.1700

Data Index: 2509108 (Open Web Text)

Max Activating Token Index: 282

Text #2

Max Range: 3.1736. Min Range: -3.1736

Max Act: 3.0512. Min Act: -0.1700

Data Index: 8824416 (Open Web Text)

Max Activating Token Index: 391

Text #3

Max Range: 3.1736. Min Range: -3.1736

Max Act: 3.0339. Min Act: -0.1700

Data Index: 574566 (Open Web Text)

Max Activating Token Index: 427

Text #4

Max Range: 3.1736. Min Range: -3.1736

Max Act: 3.0119. Min Act: -0.1700

Data Index: 140584 (Open Web Text)

Max Activating Token Index: 58

Text #5

Max Range: 3.1736. Min Range: -3.1736

Max Act: 2.9801. Min Act: -0.1700

Data Index: 3198278 (Open Web Text)

Max Activating Token Index: 308

Text #6

Max Range: 3.1736. Min Range: -3.1736

Max Act: 2.9711. Min Act: -0.1700

Data Index: 3598188 (Open Web Text)

Max Activating Token Index: 256

Text #7

Max Range: 3.1736. Min Range: -3.1736

Max Act: 2.9617. Min Act: -0.1700

Data Index: 3478402 (Open Web Text)

Max Activating Token Index: 270

Text #8

Max Range: 3.1736. Min Range: -3.1736

Max Act: 2.9395. Min Act: -0.1700

Data Index: 980434 (Open Web Text)

Max Activating Token Index: 458

Text #9

Max Range: 3.1736. Min Range: -3.1736

Max Act: 2.9552. Min Act: -0.1700

Data Index: 1968834 (Open Web Text)

Max Activating Token Index: 788

Text #10

Max Range: 3.1736. Min Range: -3.1736

Max Act: 2.9393. Min Act: -0.1700

Data Index: 8088590 (Open Web Text)

Max Activating Token Index: 117

Text #11

Max Range: 3.1736. Min Range: -3.1736

Max Act: 2.9363. Min Act: -0.1700

Data Index: 8013123 (Open Web Text)

Max Activating Token Index: 627

Text #12

Max Range: 3.1736. Min Range: -3.1736

Max Act: 2.9135. Min Act: -0.1700

Data Index: 2965141 (Open Web Text)

Max Activating Token Index: 226

Text #13

Max Range: 3.1736. Min Range: -3.1736

Max Act: 2.9131. Min Act: -0.1700

Data Index: 8620082 (Open Web Text)

Max Activating Token Index: 237

Text #14

Max Range: 3.1736. Min Range: -3.1736

Max Act: 2.9178. Min Act: -0.1700

Data Index: 4430223 (Open Web Text)

Max Activating Token Index: 995

Text #15

Max Range: 3.1736. Min Range: -3.1736

Max Act: 2.8879. Min Act: -0.1700

Data Index: 5070794 (Open Web Text)

Max Activating Token Index: 471

Text #16

Max Range: 3.1736. Min Range: -3.1736

Max Act: 2.9148. Min Act: -0.1700

Data Index: 998001 (Open Web Text)

Max Activating Token Index: 988

Text #17

Max Range: 3.1736. Min Range: -3.1736

Max Act: 2.8997. Min Act: -0.1700

Data Index: 5985207 (Open Web Text)

Max Activating Token Index: 913

Text #18

Max Range: 3.1736. Min Range: -3.1736

Max Act: 2.8895. Min Act: -0.1700

Data Index: 981611 (Open Web Text)

Max Activating Token Index: 495

Text #19

Max Range: 3.1736. Min Range: -3.1736

Max Act: 2.8757. Min Act: -0.1700

Data Index: 6934918 (Open Web Text)

Max Activating Token Index: 545