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

Dataset: Open Web Text

Neuron 1620 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: 3.1637. Min Range: -3.1637

Max Act: 3.1637. Min Act: -0.1700

Data Index: 4554822 (Open Web Text)

Max Activating Token Index: 848

Text #1

Max Range: 3.1637. Min Range: -3.1637

Max Act: 3.0646. Min Act: -0.1700

Data Index: 7614876 (Open Web Text)

Max Activating Token Index: 819

Text #2

Max Range: 3.1637. Min Range: -3.1637

Max Act: 3.1048. Min Act: -0.1700

Data Index: 1321082 (Open Web Text)

Max Activating Token Index: 769

Text #3

Max Range: 3.1637. Min Range: -3.1637

Max Act: 3.0286. Min Act: -0.1700

Data Index: 3837931 (Open Web Text)

Max Activating Token Index: 842

Text #4

Max Range: 3.1637. Min Range: -3.1637

Max Act: 3.0535. Min Act: -0.1700

Data Index: 6487443 (Open Web Text)

Max Activating Token Index: 751

Text #5

Max Range: 3.1637. Min Range: -3.1637

Max Act: 3.0481. Min Act: -0.1700

Data Index: 3676044 (Open Web Text)

Max Activating Token Index: 909

Text #6

Max Range: 3.1637. Min Range: -3.1637

Max Act: 3.0026. Min Act: -0.1700

Data Index: 2590239 (Open Web Text)

Max Activating Token Index: 998

Text #7

Max Range: 3.1637. Min Range: -3.1637

Max Act: 3.0515. Min Act: -0.1700

Data Index: 3668757 (Open Web Text)

Max Activating Token Index: 671

Text #8

Max Range: 3.1637. Min Range: -3.1637

Max Act: 3.0800. Min Act: -0.1700

Data Index: 7532569 (Open Web Text)

Max Activating Token Index: 947

Text #9

Max Range: 3.1637. Min Range: -3.1637

Max Act: 3.0076. Min Act: -0.1700

Data Index: 8096028 (Open Web Text)

Max Activating Token Index: 772

Text #10

Max Range: 3.1637. Min Range: -3.1637

Max Act: 3.0212. Min Act: -0.1700

Data Index: 4389258 (Open Web Text)

Max Activating Token Index: 693

Text #11

Max Range: 3.1637. Min Range: -3.1637

Max Act: 2.9701. Min Act: -0.1700

Data Index: 388309 (Open Web Text)

Max Activating Token Index: 429

Text #12

Max Range: 3.1637. Min Range: -3.1637

Max Act: 2.9515. Min Act: -0.1700

Data Index: 2577754 (Open Web Text)

Max Activating Token Index: 1023

Text #13

Max Range: 3.1637. Min Range: -3.1637

Max Act: 2.9737. Min Act: -0.1700

Data Index: 3202985 (Open Web Text)

Max Activating Token Index: 1023

Text #14

Max Range: 3.1637. Min Range: -3.1637

Max Act: 2.9321. Min Act: -0.1700

Data Index: 8676973 (Open Web Text)

Max Activating Token Index: 828

Text #15

Max Range: 3.1637. Min Range: -3.1637

Max Act: 2.9506. Min Act: -0.1700

Data Index: 3313191 (Open Web Text)

Max Activating Token Index: 896

Text #16

Max Range: 3.1637. Min Range: -3.1637

Max Act: 2.9359. Min Act: -0.1700

Data Index: 8614031 (Open Web Text)

Max Activating Token Index: 1023

Text #17

Max Range: 3.1637. Min Range: -3.1637

Max Act: 2.9123. Min Act: -0.1700

Data Index: 2612666 (Open Web Text)

Max Activating Token Index: 1022

Text #18

Max Range: 3.1637. Min Range: -3.1637

Max Act: 2.9035. Min Act: -0.1700

Data Index: 2486225 (Open Web Text)

Max Activating Token Index: 944

Text #19

Max Range: 3.1637. Min Range: -3.1637

Max Act: 2.9186. Min Act: -0.1700

Data Index: 2655358 (Open Web Text)

Max Activating Token Index: 890