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

Dataset: Open Web Text

Neuron 1789 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: 4.9518. Min Range: -4.9518

Max Act: 4.9518. Min Act: -0.1700

Data Index: 3336545 (Open Web Text)

Max Activating Token Index: 298

Text #1

Max Range: 4.9518. Min Range: -4.9518

Max Act: 4.9316. Min Act: -0.1700

Data Index: 5593129 (Open Web Text)

Max Activating Token Index: 319

Text #2

Max Range: 4.9518. Min Range: -4.9518

Max Act: 4.8998. Min Act: -0.1700

Data Index: 6806170 (Open Web Text)

Max Activating Token Index: 228

Text #3

Max Range: 4.9518. Min Range: -4.9518

Max Act: 4.8883. Min Act: -0.1700

Data Index: 2224343 (Open Web Text)

Max Activating Token Index: 236

Text #4

Max Range: 4.9518. Min Range: -4.9518

Max Act: 4.8262. Min Act: -0.1700

Data Index: 2896288 (Open Web Text)

Max Activating Token Index: 708

Text #5

Max Range: 4.9518. Min Range: -4.9518

Max Act: 4.8213. Min Act: -0.1700

Data Index: 8288072 (Open Web Text)

Max Activating Token Index: 979

Text #6

Max Range: 4.9518. Min Range: -4.9518

Max Act: 4.8755. Min Act: -0.1700

Data Index: 2633124 (Open Web Text)

Max Activating Token Index: 244

Text #7

Max Range: 4.9518. Min Range: -4.9518

Max Act: 4.9150. Min Act: -0.1700

Data Index: 6707246 (Open Web Text)

Max Activating Token Index: 202

Text #8

Max Range: 4.9518. Min Range: -4.9518

Max Act: 4.8430. Min Act: -0.1700

Data Index: 6243996 (Open Web Text)

Max Activating Token Index: 236

Text #9

Max Range: 4.9518. Min Range: -4.9518

Max Act: 4.8015. Min Act: -0.1700

Data Index: 5835847 (Open Web Text)

Max Activating Token Index: 809

Text #10

Max Range: 4.9518. Min Range: -4.9518

Max Act: 4.8567. Min Act: -0.1700

Data Index: 5792636 (Open Web Text)

Max Activating Token Index: 686

Text #11

Max Range: 4.9518. Min Range: -4.9518

Max Act: 4.9048. Min Act: -0.1700

Data Index: 7007480 (Open Web Text)

Max Activating Token Index: 1020

Text #12

Max Range: 4.9518. Min Range: -4.9518

Max Act: 4.8349. Min Act: -0.1700

Data Index: 2666152 (Open Web Text)

Max Activating Token Index: 869

Text #13

Max Range: 4.9518. Min Range: -4.9518

Max Act: 4.8110. Min Act: -0.1700

Data Index: 6868281 (Open Web Text)

Max Activating Token Index: 675

Text #14

Max Range: 4.9518. Min Range: -4.9518

Max Act: 4.9031. Min Act: -0.1700

Data Index: 4799391 (Open Web Text)

Max Activating Token Index: 320

Text #15

Max Range: 4.9518. Min Range: -4.9518

Max Act: 4.8160. Min Act: -0.1700

Data Index: 650349 (Open Web Text)

Max Activating Token Index: 141

Text #16

Max Range: 4.9518. Min Range: -4.9518

Max Act: 4.7609. Min Act: -0.1700

Data Index: 1660857 (Open Web Text)

Max Activating Token Index: 495

Text #17

Max Range: 4.9518. Min Range: -4.9518

Max Act: 4.7754. Min Act: -0.1700

Data Index: 6756562 (Open Web Text)

Max Activating Token Index: 1022

Text #18

Max Range: 4.9518. Min Range: -4.9518

Max Act: 4.7933. Min Act: -0.1700

Data Index: 5764780 (Open Web Text)

Max Activating Token Index: 737

Text #19

Max Range: 4.9518. Min Range: -4.9518

Max Act: 4.8589. Min Act: -0.1700

Data Index: 2179115 (Open Web Text)

Max Activating Token Index: 766