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

Dataset: Open Web Text

Neuron 2365 in Layer 5

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: 4.4635. Min Range: -4.4635

Max Act: 4.4635. Min Act: -0.1700

Data Index: 6295956 (Open Web Text)

Max Activating Token Index: 345

Text #1

Max Range: 4.4635. Min Range: -4.4635

Max Act: 4.2186. Min Act: -0.1700

Data Index: 2904437 (Open Web Text)

Max Activating Token Index: 347

Text #2

Max Range: 4.4635. Min Range: -4.4635

Max Act: 4.1426. Min Act: -0.1700

Data Index: 6798188 (Open Web Text)

Max Activating Token Index: 725

Text #3

Max Range: 4.4635. Min Range: -4.4635

Max Act: 4.1721. Min Act: -0.1700

Data Index: 3466406 (Open Web Text)

Max Activating Token Index: 241

Text #4

Max Range: 4.4635. Min Range: -4.4635

Max Act: 4.1365. Min Act: -0.1700

Data Index: 6072502 (Open Web Text)

Max Activating Token Index: 624

Text #5

Max Range: 4.4635. Min Range: -4.4635

Max Act: 4.1162. Min Act: -0.1700

Data Index: 4852211 (Open Web Text)

Max Activating Token Index: 682

Text #6

Max Range: 4.4635. Min Range: -4.4635

Max Act: 4.1230. Min Act: -0.1700

Data Index: 5455430 (Open Web Text)

Max Activating Token Index: 620

Text #7

Max Range: 4.4635. Min Range: -4.4635

Max Act: 4.1117. Min Act: -0.1700

Data Index: 6715809 (Open Web Text)

Max Activating Token Index: 720

Text #8

Max Range: 4.4635. Min Range: -4.4635

Max Act: 4.1141. Min Act: -0.1700

Data Index: 8359105 (Open Web Text)

Max Activating Token Index: 828

Text #9

Max Range: 4.4635. Min Range: -4.4635

Max Act: 4.0834. Min Act: -0.1700

Data Index: 5821302 (Open Web Text)

Max Activating Token Index: 224

Text #10

Max Range: 4.4635. Min Range: -4.4635

Max Act: 4.0466. Min Act: -0.1700

Data Index: 6740567 (Open Web Text)

Max Activating Token Index: 918

Text #11

Max Range: 4.4635. Min Range: -4.4635

Max Act: 4.0837. Min Act: -0.1700

Data Index: 6379088 (Open Web Text)

Max Activating Token Index: 559

Text #12

Max Range: 4.4635. Min Range: -4.4635

Max Act: 4.0581. Min Act: -0.1700

Data Index: 6655924 (Open Web Text)

Max Activating Token Index: 544

Text #13

Max Range: 4.4635. Min Range: -4.4635

Max Act: 4.0444. Min Act: -0.1700

Data Index: 6398667 (Open Web Text)

Max Activating Token Index: 71

Text #14

Max Range: 4.4635. Min Range: -4.4635

Max Act: 4.0384. Min Act: -0.1700

Data Index: 3058909 (Open Web Text)

Max Activating Token Index: 882

Text #15

Max Range: 4.4635. Min Range: -4.4635

Max Act: 4.0292. Min Act: -0.1700

Data Index: 5805189 (Open Web Text)

Max Activating Token Index: 962

Text #16

Max Range: 4.4635. Min Range: -4.4635

Max Act: 4.0413. Min Act: -0.1700

Data Index: 6303918 (Open Web Text)

Max Activating Token Index: 416

Text #17

Max Range: 4.4635. Min Range: -4.4635

Max Act: 3.9881. Min Act: -0.1700

Data Index: 3628486 (Open Web Text)

Max Activating Token Index: 858

Text #18

Max Range: 4.4635. Min Range: -4.4635

Max Act: 3.9791. Min Act: -0.1700

Data Index: 4899040 (Open Web Text)

Max Activating Token Index: 420

Text #19

Max Range: 4.4635. Min Range: -4.4635

Max Act: 3.9411. Min Act: -0.1700

Data Index: 4485129 (Open Web Text)

Max Activating Token Index: 804