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

Dataset: Open Web Text

Neuron 2070 in Layer 3

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: 4.5488. Min Range: -4.5488

Max Act: 4.5488. Min Act: -0.1700

Data Index: 1972141 (Open Web Text)

Max Activating Token Index: 972

Text #1

Max Range: 4.5488. Min Range: -4.5488

Max Act: 4.5020. Min Act: -0.1700

Data Index: 5393205 (Open Web Text)

Max Activating Token Index: 434

Text #2

Max Range: 4.5488. Min Range: -4.5488

Max Act: 4.4508. Min Act: -0.1700

Data Index: 4848814 (Open Web Text)

Max Activating Token Index: 748

Text #3

Max Range: 4.5488. Min Range: -4.5488

Max Act: 4.4195. Min Act: -0.1700

Data Index: 8710469 (Open Web Text)

Max Activating Token Index: 626

Text #4

Max Range: 4.5488. Min Range: -4.5488

Max Act: 4.4728. Min Act: -0.1700

Data Index: 4806768 (Open Web Text)

Max Activating Token Index: 820

Text #5

Max Range: 4.5488. Min Range: -4.5488

Max Act: 4.3864. Min Act: -0.1700

Data Index: 1368139 (Open Web Text)

Max Activating Token Index: 875

Text #6

Max Range: 4.5488. Min Range: -4.5488

Max Act: 4.4168. Min Act: -0.1700

Data Index: 3124831 (Open Web Text)

Max Activating Token Index: 605

Text #7

Max Range: 4.5488. Min Range: -4.5488

Max Act: 4.4210. Min Act: -0.1700

Data Index: 2768276 (Open Web Text)

Max Activating Token Index: 929

Text #8

Max Range: 4.5488. Min Range: -4.5488

Max Act: 4.3898. Min Act: -0.1700

Data Index: 6647981 (Open Web Text)

Max Activating Token Index: 424

Text #9

Max Range: 4.5488. Min Range: -4.5488

Max Act: 4.4116. Min Act: -0.1700

Data Index: 1136572 (Open Web Text)

Max Activating Token Index: 595

Text #10

Max Range: 4.5488. Min Range: -4.5488

Max Act: 4.3941. Min Act: -0.1700

Data Index: 6511337 (Open Web Text)

Max Activating Token Index: 909

Text #11

Max Range: 4.5488. Min Range: -4.5488

Max Act: 4.3841. Min Act: -0.1700

Data Index: 5456013 (Open Web Text)

Max Activating Token Index: 697

Text #12

Max Range: 4.5488. Min Range: -4.5488

Max Act: 4.3974. Min Act: -0.1700

Data Index: 6308270 (Open Web Text)

Max Activating Token Index: 1006

Text #13

Max Range: 4.5488. Min Range: -4.5488

Max Act: 4.3589. Min Act: -0.1700

Data Index: 5848986 (Open Web Text)

Max Activating Token Index: 18

Text #14

Max Range: 4.5488. Min Range: -4.5488

Max Act: 4.3897. Min Act: -0.1700

Data Index: 7188350 (Open Web Text)

Max Activating Token Index: 461

Text #15

Max Range: 4.5488. Min Range: -4.5488

Max Act: 4.3736. Min Act: -0.1700

Data Index: 2356416 (Open Web Text)

Max Activating Token Index: 706

Text #16

Max Range: 4.5488. Min Range: -4.5488

Max Act: 4.3949. Min Act: -0.1700

Data Index: 3606089 (Open Web Text)

Max Activating Token Index: 23

Text #17

Max Range: 4.5488. Min Range: -4.5488

Max Act: 4.3871. Min Act: -0.1700

Data Index: 8081010 (Open Web Text)

Max Activating Token Index: 663

Text #18

Max Range: 4.5488. Min Range: -4.5488

Max Act: 4.3923. Min Act: -0.1700

Data Index: 6296355 (Open Web Text)

Max Activating Token Index: 19

Text #19

Max Range: 4.5488. Min Range: -4.5488

Max Act: 4.4044. Min Act: -0.1700

Data Index: 857124 (Open Web Text)

Max Activating Token Index: 857