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

Dataset: Open Web Text

Neuron 217 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: 3.1225. Min Range: -3.1225

Max Act: 3.1225. Min Act: -0.1700

Data Index: 3181043 (Open Web Text)

Max Activating Token Index: 841

Text #1

Max Range: 3.1225. Min Range: -3.1225

Max Act: 3.0072. Min Act: -0.1700

Data Index: 6870335 (Open Web Text)

Max Activating Token Index: 180

Text #2

Max Range: 3.1225. Min Range: -3.1225

Max Act: 2.9818. Min Act: -0.1700

Data Index: 8303402 (Open Web Text)

Max Activating Token Index: 286

Text #3

Max Range: 3.1225. Min Range: -3.1225

Max Act: 2.9294. Min Act: -0.1700

Data Index: 8787608 (Open Web Text)

Max Activating Token Index: 479

Text #4

Max Range: 3.1225. Min Range: -3.1225

Max Act: 2.9329. Min Act: -0.1700

Data Index: 5331039 (Open Web Text)

Max Activating Token Index: 863

Text #5

Max Range: 3.1225. Min Range: -3.1225

Max Act: 2.9171. Min Act: -0.1700

Data Index: 6030351 (Open Web Text)

Max Activating Token Index: 821

Text #6

Max Range: 3.1225. Min Range: -3.1225

Max Act: 2.9160. Min Act: -0.1700

Data Index: 3769935 (Open Web Text)

Max Activating Token Index: 613

Text #7

Max Range: 3.1225. Min Range: -3.1225

Max Act: 2.9167. Min Act: -0.1700

Data Index: 53910 (Open Web Text)

Max Activating Token Index: 954

Text #8

Max Range: 3.1225. Min Range: -3.1225

Max Act: 2.9159. Min Act: -0.1700

Data Index: 1852252 (Open Web Text)

Max Activating Token Index: 27

Text #9

Max Range: 3.1225. Min Range: -3.1225

Max Act: 2.8851. Min Act: -0.1700

Data Index: 4052602 (Open Web Text)

Max Activating Token Index: 385

Text #10

Max Range: 3.1225. Min Range: -3.1225

Max Act: 2.8807. Min Act: -0.1700

Data Index: 8547325 (Open Web Text)

Max Activating Token Index: 855

Text #11

Max Range: 3.1225. Min Range: -3.1225

Max Act: 2.8924. Min Act: -0.1700

Data Index: 8671612 (Open Web Text)

Max Activating Token Index: 551

Text #12

Max Range: 3.1225. Min Range: -3.1225

Max Act: 2.8194. Min Act: -0.1700

Data Index: 4927857 (Open Web Text)

Max Activating Token Index: 926

Text #13

Max Range: 3.1225. Min Range: -3.1225

Max Act: 2.8580. Min Act: -0.1700

Data Index: 6394718 (Open Web Text)

Max Activating Token Index: 48

Text #14

Max Range: 3.1225. Min Range: -3.1225

Max Act: 2.8377. Min Act: -0.1700

Data Index: 6403535 (Open Web Text)

Max Activating Token Index: 8

Text #15

Max Range: 3.1225. Min Range: -3.1225

Max Act: 2.8487. Min Act: -0.1700

Data Index: 4225481 (Open Web Text)

Max Activating Token Index: 7

Text #16

Max Range: 3.1225. Min Range: -3.1225

Max Act: 2.8684. Min Act: -0.1700

Data Index: 8260914 (Open Web Text)

Max Activating Token Index: 904

Text #17

Max Range: 3.1225. Min Range: -3.1225

Max Act: 2.8415. Min Act: -0.1700

Data Index: 4747042 (Open Web Text)

Max Activating Token Index: 78

Text #18

Max Range: 3.1225. Min Range: -3.1225

Max Act: 2.8449. Min Act: -0.1700

Data Index: 3013994 (Open Web Text)

Max Activating Token Index: 4

Text #19

Max Range: 3.1225. Min Range: -3.1225

Max Act: 2.8462. Min Act: -0.1700

Data Index: 1774040 (Open Web Text)

Max Activating Token Index: 95