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

Dataset: Open Web Text

Neuron 1831 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: 4.6247. Min Range: -4.6247

Max Act: 4.6247. Min Act: -0.1700

Data Index: 850818 (Open Web Text)

Max Activating Token Index: 303

Text #1

Max Range: 4.6247. Min Range: -4.6247

Max Act: 4.5032. Min Act: -0.1700

Data Index: 1261824 (Open Web Text)

Max Activating Token Index: 232

Text #2

Max Range: 4.6247. Min Range: -4.6247

Max Act: 4.5198. Min Act: -0.1700

Data Index: 639321 (Open Web Text)

Max Activating Token Index: 507

Text #3

Max Range: 4.6247. Min Range: -4.6247

Max Act: 4.4305. Min Act: -0.1700

Data Index: 943922 (Open Web Text)

Max Activating Token Index: 600

Text #4

Max Range: 4.6247. Min Range: -4.6247

Max Act: 4.4564. Min Act: -0.1700

Data Index: 3614472 (Open Web Text)

Max Activating Token Index: 657

Text #5

Max Range: 4.6247. Min Range: -4.6247

Max Act: 4.4337. Min Act: -0.1700

Data Index: 2424770 (Open Web Text)

Max Activating Token Index: 672

Text #6

Max Range: 4.6247. Min Range: -4.6247

Max Act: 4.3705. Min Act: -0.1700

Data Index: 7911777 (Open Web Text)

Max Activating Token Index: 241

Text #7

Max Range: 4.6247. Min Range: -4.6247

Max Act: 4.3881. Min Act: -0.1700

Data Index: 4306077 (Open Web Text)

Max Activating Token Index: 1018

Text #8

Max Range: 4.6247. Min Range: -4.6247

Max Act: 4.3728. Min Act: -0.1700

Data Index: 3994819 (Open Web Text)

Max Activating Token Index: 729

Text #9

Max Range: 4.6247. Min Range: -4.6247

Max Act: 4.3683. Min Act: -0.1700

Data Index: 8397623 (Open Web Text)

Max Activating Token Index: 569

Text #10

Max Range: 4.6247. Min Range: -4.6247

Max Act: 4.3779. Min Act: -0.1700

Data Index: 7272416 (Open Web Text)

Max Activating Token Index: 936

Text #11

Max Range: 4.6247. Min Range: -4.6247

Max Act: 4.3637. Min Act: -0.1700

Data Index: 1967375 (Open Web Text)

Max Activating Token Index: 216

Text #12

Max Range: 4.6247. Min Range: -4.6247

Max Act: 4.3620. Min Act: -0.1700

Data Index: 1786400 (Open Web Text)

Max Activating Token Index: 565

Text #13

Max Range: 4.6247. Min Range: -4.6247

Max Act: 4.3497. Min Act: -0.1700

Data Index: 286967 (Open Web Text)

Max Activating Token Index: 173

Text #14

Max Range: 4.6247. Min Range: -4.6247

Max Act: 4.3544. Min Act: -0.1700

Data Index: 451096 (Open Web Text)

Max Activating Token Index: 970

Text #15

Max Range: 4.6247. Min Range: -4.6247

Max Act: 4.3488. Min Act: -0.1700

Data Index: 7598080 (Open Web Text)

Max Activating Token Index: 697

Text #16

Max Range: 4.6247. Min Range: -4.6247

Max Act: 4.3600. Min Act: -0.1700

Data Index: 5504375 (Open Web Text)

Max Activating Token Index: 696

Text #17

Max Range: 4.6247. Min Range: -4.6247

Max Act: 4.3530. Min Act: -0.1700

Data Index: 1387974 (Open Web Text)

Max Activating Token Index: 498

Text #18

Max Range: 4.6247. Min Range: -4.6247

Max Act: 4.3223. Min Act: -0.1700

Data Index: 218299 (Open Web Text)

Max Activating Token Index: 570

Text #19

Max Range: 4.6247. Min Range: -4.6247

Max Act: 4.3417. Min Act: -0.1700

Data Index: 3583956 (Open Web Text)

Max Activating Token Index: 360