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

Dataset: Open Web Text

Neuron 608 in Layer 4

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: 4.2088. Min Range: -4.2088

Max Act: 4.2088. Min Act: -0.1700

Data Index: 7971367 (Open Web Text)

Max Activating Token Index: 516

Text #1

Max Range: 4.2088. Min Range: -4.2088

Max Act: 4.1793. Min Act: -0.1700

Data Index: 1265982 (Open Web Text)

Max Activating Token Index: 451

Text #2

Max Range: 4.2088. Min Range: -4.2088

Max Act: 4.1716. Min Act: -0.1700

Data Index: 8493281 (Open Web Text)

Max Activating Token Index: 192

Text #3

Max Range: 4.2088. Min Range: -4.2088

Max Act: 4.1114. Min Act: -0.1700

Data Index: 4555226 (Open Web Text)

Max Activating Token Index: 316

Text #4

Max Range: 4.2088. Min Range: -4.2088

Max Act: 4.1206. Min Act: -0.1700

Data Index: 3362814 (Open Web Text)

Max Activating Token Index: 16

Text #5

Max Range: 4.2088. Min Range: -4.2088

Max Act: 4.0973. Min Act: -0.1700

Data Index: 4432650 (Open Web Text)

Max Activating Token Index: 325

Text #6

Max Range: 4.2088. Min Range: -4.2088

Max Act: 4.0444. Min Act: -0.1700

Data Index: 7191971 (Open Web Text)

Max Activating Token Index: 307

Text #7

Max Range: 4.2088. Min Range: -4.2088

Max Act: 4.0499. Min Act: -0.1700

Data Index: 6027980 (Open Web Text)

Max Activating Token Index: 347

Text #8

Max Range: 4.2088. Min Range: -4.2088

Max Act: 4.0447. Min Act: -0.1700

Data Index: 6033362 (Open Web Text)

Max Activating Token Index: 493

Text #9

Max Range: 4.2088. Min Range: -4.2088

Max Act: 4.0382. Min Act: -0.1700

Data Index: 750227 (Open Web Text)

Max Activating Token Index: 780

Text #10

Max Range: 4.2088. Min Range: -4.2088

Max Act: 4.0596. Min Act: -0.1700

Data Index: 209818 (Open Web Text)

Max Activating Token Index: 156

Text #11

Max Range: 4.2088. Min Range: -4.2088

Max Act: 4.0506. Min Act: -0.1700

Data Index: 2694009 (Open Web Text)

Max Activating Token Index: 528

Text #12

Max Range: 4.2088. Min Range: -4.2088

Max Act: 4.0410. Min Act: -0.1700

Data Index: 6034521 (Open Web Text)

Max Activating Token Index: 85

Text #13

Max Range: 4.2088. Min Range: -4.2088

Max Act: 4.0292. Min Act: -0.1700

Data Index: 4176873 (Open Web Text)

Max Activating Token Index: 582

Text #14

Max Range: 4.2088. Min Range: -4.2088

Max Act: 4.0109. Min Act: -0.1700

Data Index: 6760006 (Open Web Text)

Max Activating Token Index: 907

Text #15

Max Range: 4.2088. Min Range: -4.2088

Max Act: 3.9981. Min Act: -0.1700

Data Index: 6566237 (Open Web Text)

Max Activating Token Index: 186

Text #16

Max Range: 4.2088. Min Range: -4.2088

Max Act: 4.0086. Min Act: -0.1700

Data Index: 2938488 (Open Web Text)

Max Activating Token Index: 748

Text #17

Max Range: 4.2088. Min Range: -4.2088

Max Act: 4.0178. Min Act: -0.1700

Data Index: 6367463 (Open Web Text)

Max Activating Token Index: 68

Text #18

Max Range: 4.2088. Min Range: -4.2088

Max Act: 4.0190. Min Act: -0.1700

Data Index: 3939431 (Open Web Text)

Max Activating Token Index: 921

Text #19

Max Range: 4.2088. Min Range: -4.2088

Max Act: 4.0099. Min Act: -0.1700

Data Index: 1746510 (Open Web Text)

Max Activating Token Index: 327