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

Dataset: Open Web Text

Neuron 1323 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: 4.7885. Min Range: -4.7885

Max Act: 4.7885. Min Act: -0.1700

Data Index: 3772844 (Open Web Text)

Max Activating Token Index: 161

Text #1

Max Range: 4.7885. Min Range: -4.7885

Max Act: 4.7676. Min Act: -0.1700

Data Index: 836572 (Open Web Text)

Max Activating Token Index: 594

Text #2

Max Range: 4.7885. Min Range: -4.7885

Max Act: 4.7358. Min Act: -0.1700

Data Index: 2778018 (Open Web Text)

Max Activating Token Index: 492

Text #3

Max Range: 4.7885. Min Range: -4.7885

Max Act: 4.6731. Min Act: -0.1700

Data Index: 5546853 (Open Web Text)

Max Activating Token Index: 946

Text #4

Max Range: 4.7885. Min Range: -4.7885

Max Act: 4.6605. Min Act: -0.1700

Data Index: 5461332 (Open Web Text)

Max Activating Token Index: 309

Text #5

Max Range: 4.7885. Min Range: -4.7885

Max Act: 4.6229. Min Act: -0.1700

Data Index: 1267218 (Open Web Text)

Max Activating Token Index: 401

Text #6

Max Range: 4.7885. Min Range: -4.7885

Max Act: 4.6606. Min Act: -0.1700

Data Index: 5595096 (Open Web Text)

Max Activating Token Index: 914

Text #7

Max Range: 4.7885. Min Range: -4.7885

Max Act: 4.6326. Min Act: -0.1700

Data Index: 5443477 (Open Web Text)

Max Activating Token Index: 860

Text #8

Max Range: 4.7885. Min Range: -4.7885

Max Act: 4.6290. Min Act: -0.1700

Data Index: 3930437 (Open Web Text)

Max Activating Token Index: 877

Text #9

Max Range: 4.7885. Min Range: -4.7885

Max Act: 4.6087. Min Act: -0.1700

Data Index: 3988387 (Open Web Text)

Max Activating Token Index: 401

Text #10

Max Range: 4.7885. Min Range: -4.7885

Max Act: 4.6472. Min Act: -0.1700

Data Index: 8692868 (Open Web Text)

Max Activating Token Index: 782

Text #11

Max Range: 4.7885. Min Range: -4.7885

Max Act: 4.6077. Min Act: -0.1700

Data Index: 8789800 (Open Web Text)

Max Activating Token Index: 280

Text #12

Max Range: 4.7885. Min Range: -4.7885

Max Act: 4.5966. Min Act: -0.1700

Data Index: 4164637 (Open Web Text)

Max Activating Token Index: 592

Text #13

Max Range: 4.7885. Min Range: -4.7885

Max Act: 4.5837. Min Act: -0.1700

Data Index: 1115966 (Open Web Text)

Max Activating Token Index: 960

Text #14

Max Range: 4.7885. Min Range: -4.7885

Max Act: 4.5936. Min Act: -0.1700

Data Index: 1520483 (Open Web Text)

Max Activating Token Index: 898

Text #15

Max Range: 4.7885. Min Range: -4.7885

Max Act: 4.5261. Min Act: -0.1700

Data Index: 8179179 (Open Web Text)

Max Activating Token Index: 959

Text #16

Max Range: 4.7885. Min Range: -4.7885

Max Act: 4.5451. Min Act: -0.1700

Data Index: 655132 (Open Web Text)

Max Activating Token Index: 852

Text #17

Max Range: 4.7885. Min Range: -4.7885

Max Act: 4.5442. Min Act: -0.1700

Data Index: 7136206 (Open Web Text)

Max Activating Token Index: 683

Text #18

Max Range: 4.7885. Min Range: -4.7885

Max Act: 4.5692. Min Act: -0.1700

Data Index: 6489778 (Open Web Text)

Max Activating Token Index: 677

Text #19

Max Range: 4.7885. Min Range: -4.7885

Max Act: 4.5636. Min Act: -0.1700

Data Index: 849506 (Open Web Text)

Max Activating Token Index: 548