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

Dataset: Open Web Text

Neuron 379 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: 4.9816. Min Range: -4.9816

Max Act: 4.9646. Min Act: -0.1700

Data Index: 951756 (Open Web Text)

Max Activating Token Index: 1015

Text #1

Max Range: 4.9816. Min Range: -4.9816

Max Act: 4.9816. Min Act: -0.1700

Data Index: 7799700 (Open Web Text)

Max Activating Token Index: 305

Text #2

Max Range: 4.9816. Min Range: -4.9816

Max Act: 4.9597. Min Act: -0.1700

Data Index: 6069095 (Open Web Text)

Max Activating Token Index: 588

Text #3

Max Range: 4.9816. Min Range: -4.9816

Max Act: 4.9441. Min Act: -0.1700

Data Index: 7472753 (Open Web Text)

Max Activating Token Index: 988

Text #4

Max Range: 4.9816. Min Range: -4.9816

Max Act: 4.9368. Min Act: -0.1700

Data Index: 7863825 (Open Web Text)

Max Activating Token Index: 358

Text #5

Max Range: 4.9816. Min Range: -4.9816

Max Act: 4.9424. Min Act: -0.1700

Data Index: 7843471 (Open Web Text)

Max Activating Token Index: 973

Text #6

Max Range: 4.9816. Min Range: -4.9816

Max Act: 4.8971. Min Act: -0.1700

Data Index: 5639246 (Open Web Text)

Max Activating Token Index: 175

Text #7

Max Range: 4.9816. Min Range: -4.9816

Max Act: 4.9046. Min Act: -0.1700

Data Index: 8396118 (Open Web Text)

Max Activating Token Index: 307

Text #8

Max Range: 4.9816. Min Range: -4.9816

Max Act: 4.9293. Min Act: -0.1700

Data Index: 1826287 (Open Web Text)

Max Activating Token Index: 533

Text #9

Max Range: 4.9816. Min Range: -4.9816

Max Act: 4.8712. Min Act: -0.1700

Data Index: 5540331 (Open Web Text)

Max Activating Token Index: 596

Text #10

Max Range: 4.9816. Min Range: -4.9816

Max Act: 4.8620. Min Act: -0.1700

Data Index: 7799698 (Open Web Text)

Max Activating Token Index: 173

Text #11

Max Range: 4.9816. Min Range: -4.9816

Max Act: 4.8249. Min Act: -0.1700

Data Index: 2982363 (Open Web Text)

Max Activating Token Index: 659

Text #12

Max Range: 4.9816. Min Range: -4.9816

Max Act: 4.8251. Min Act: -0.1700

Data Index: 8198500 (Open Web Text)

Max Activating Token Index: 72

Text #13

Max Range: 4.9816. Min Range: -4.9816

Max Act: 4.8518. Min Act: -0.1700

Data Index: 1520205 (Open Web Text)

Max Activating Token Index: 655

Text #14

Max Range: 4.9816. Min Range: -4.9816

Max Act: 4.8273. Min Act: -0.1700

Data Index: 1617803 (Open Web Text)

Max Activating Token Index: 1001

Text #15

Max Range: 4.9816. Min Range: -4.9816

Max Act: 4.8460. Min Act: -0.1700

Data Index: 2636643 (Open Web Text)

Max Activating Token Index: 1007

Text #16

Max Range: 4.9816. Min Range: -4.9816

Max Act: 4.8152. Min Act: -0.1700

Data Index: 315138 (Open Web Text)

Max Activating Token Index: 753

Text #17

Max Range: 4.9816. Min Range: -4.9816

Max Act: 4.7853. Min Act: -0.1700

Data Index: 3716369 (Open Web Text)

Max Activating Token Index: 470

Text #18

Max Range: 4.9816. Min Range: -4.9816

Max Act: 4.7912. Min Act: -0.1700

Data Index: 403953 (Open Web Text)

Max Activating Token Index: 207

Text #19

Max Range: 4.9816. Min Range: -4.9816

Max Act: 4.7686. Min Act: -0.1700

Data Index: 71937 (Open Web Text)

Max Activating Token Index: 645