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

Dataset: Open Web Text

Neuron 1452 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: 3.7400. Min Range: -3.7400

Max Act: 3.7400. Min Act: -0.1700

Data Index: 3181063 (Open Web Text)

Max Activating Token Index: 1005

Text #1

Max Range: 3.7400. Min Range: -3.7400

Max Act: 3.6623. Min Act: -0.1700

Data Index: 2405335 (Open Web Text)

Max Activating Token Index: 555

Text #2

Max Range: 3.7400. Min Range: -3.7400

Max Act: 3.6753. Min Act: -0.1700

Data Index: 3608556 (Open Web Text)

Max Activating Token Index: 485

Text #3

Max Range: 3.7400. Min Range: -3.7400

Max Act: 3.6536. Min Act: -0.1700

Data Index: 861318 (Open Web Text)

Max Activating Token Index: 877

Text #4

Max Range: 3.7400. Min Range: -3.7400

Max Act: 3.6298. Min Act: -0.1700

Data Index: 1632222 (Open Web Text)

Max Activating Token Index: 1018

Text #5

Max Range: 3.7400. Min Range: -3.7400

Max Act: 3.6210. Min Act: -0.1700

Data Index: 46785 (Open Web Text)

Max Activating Token Index: 11

Text #6

Max Range: 3.7400. Min Range: -3.7400

Max Act: 3.6304. Min Act: -0.1700

Data Index: 7920467 (Open Web Text)

Max Activating Token Index: 673

Text #7

Max Range: 3.7400. Min Range: -3.7400

Max Act: 3.6309. Min Act: -0.1700

Data Index: 2765208 (Open Web Text)

Max Activating Token Index: 392

Text #8

Max Range: 3.7400. Min Range: -3.7400

Max Act: 3.5965. Min Act: -0.1700

Data Index: 2729367 (Open Web Text)

Max Activating Token Index: 757

Text #9

Max Range: 3.7400. Min Range: -3.7400

Max Act: 3.6274. Min Act: -0.1700

Data Index: 4586927 (Open Web Text)

Max Activating Token Index: 706

Text #10

Max Range: 3.7400. Min Range: -3.7400

Max Act: 3.5719. Min Act: -0.1700

Data Index: 7308139 (Open Web Text)

Max Activating Token Index: 431

Text #11

Max Range: 3.7400. Min Range: -3.7400

Max Act: 3.5925. Min Act: -0.1700

Data Index: 398597 (Open Web Text)

Max Activating Token Index: 869

Text #12

Max Range: 3.7400. Min Range: -3.7400

Max Act: 3.6129. Min Act: -0.1700

Data Index: 5357641 (Open Web Text)

Max Activating Token Index: 992

Text #13

Max Range: 3.7400. Min Range: -3.7400

Max Act: 3.6072. Min Act: -0.1700

Data Index: 3395705 (Open Web Text)

Max Activating Token Index: 493

Text #14

Max Range: 3.7400. Min Range: -3.7400

Max Act: 3.6063. Min Act: -0.1700

Data Index: 2337931 (Open Web Text)

Max Activating Token Index: 22

Text #15

Max Range: 3.7400. Min Range: -3.7400

Max Act: 3.5892. Min Act: -0.1700

Data Index: 1936997 (Open Web Text)

Max Activating Token Index: 892

Text #16

Max Range: 3.7400. Min Range: -3.7400

Max Act: 3.6046. Min Act: -0.1700

Data Index: 4025180 (Open Web Text)

Max Activating Token Index: 904

Text #17

Max Range: 3.7400. Min Range: -3.7400

Max Act: 3.5951. Min Act: -0.1700

Data Index: 279690 (Open Web Text)

Max Activating Token Index: 347

Text #18

Max Range: 3.7400. Min Range: -3.7400

Max Act: 3.5809. Min Act: -0.1700

Data Index: 613639 (Open Web Text)

Max Activating Token Index: 469

Text #19

Max Range: 3.7400. Min Range: -3.7400

Max Act: 3.5923. Min Act: -0.1700

Data Index: 1754790 (Open Web Text)

Max Activating Token Index: 332