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

Dataset: Open Web Text

Neuron 2167 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: 4.3678. Min Range: -4.3678

Max Act: 4.3678. Min Act: -0.1700

Data Index: 1796270 (Open Web Text)

Max Activating Token Index: 818

Text #1

Max Range: 4.3678. Min Range: -4.3678

Max Act: 4.3475. Min Act: -0.1700

Data Index: 1796274 (Open Web Text)

Max Activating Token Index: 915

Text #2

Max Range: 4.3678. Min Range: -4.3678

Max Act: 4.3063. Min Act: -0.1700

Data Index: 5058265 (Open Web Text)

Max Activating Token Index: 803

Text #3

Max Range: 4.3678. Min Range: -4.3678

Max Act: 4.2612. Min Act: -0.1700

Data Index: 317294 (Open Web Text)

Max Activating Token Index: 425

Text #4

Max Range: 4.3678. Min Range: -4.3678

Max Act: 4.1937. Min Act: -0.1700

Data Index: 7355884 (Open Web Text)

Max Activating Token Index: 741

Text #5

Max Range: 4.3678. Min Range: -4.3678

Max Act: 4.2316. Min Act: -0.1700

Data Index: 1874814 (Open Web Text)

Max Activating Token Index: 224

Text #6

Max Range: 4.3678. Min Range: -4.3678

Max Act: 4.1921. Min Act: -0.1700

Data Index: 4091926 (Open Web Text)

Max Activating Token Index: 462

Text #7

Max Range: 4.3678. Min Range: -4.3678

Max Act: 4.1965. Min Act: -0.1700

Data Index: 6145376 (Open Web Text)

Max Activating Token Index: 429

Text #8

Max Range: 4.3678. Min Range: -4.3678

Max Act: 4.1773. Min Act: -0.1700

Data Index: 2136503 (Open Web Text)

Max Activating Token Index: 453

Text #9

Max Range: 4.3678. Min Range: -4.3678

Max Act: 4.1913. Min Act: -0.1700

Data Index: 3111767 (Open Web Text)

Max Activating Token Index: 471

Text #10

Max Range: 4.3678. Min Range: -4.3678

Max Act: 4.1867. Min Act: -0.1700

Data Index: 6566064 (Open Web Text)

Max Activating Token Index: 198

Text #11

Max Range: 4.3678. Min Range: -4.3678

Max Act: 4.1672. Min Act: -0.1700

Data Index: 3563338 (Open Web Text)

Max Activating Token Index: 229

Text #12

Max Range: 4.3678. Min Range: -4.3678

Max Act: 4.1609. Min Act: -0.1700

Data Index: 1754348 (Open Web Text)

Max Activating Token Index: 691

Text #13

Max Range: 4.3678. Min Range: -4.3678

Max Act: 4.1375. Min Act: -0.1700

Data Index: 6545235 (Open Web Text)

Max Activating Token Index: 752

Text #14

Max Range: 4.3678. Min Range: -4.3678

Max Act: 4.1315. Min Act: -0.1700

Data Index: 5756406 (Open Web Text)

Max Activating Token Index: 31

Text #15

Max Range: 4.3678. Min Range: -4.3678

Max Act: 4.1381. Min Act: -0.1700

Data Index: 5655887 (Open Web Text)

Max Activating Token Index: 321

Text #16

Max Range: 4.3678. Min Range: -4.3678

Max Act: 4.1442. Min Act: -0.1700

Data Index: 7646408 (Open Web Text)

Max Activating Token Index: 644

Text #17

Max Range: 4.3678. Min Range: -4.3678

Max Act: 4.1190. Min Act: -0.1700

Data Index: 3447433 (Open Web Text)

Max Activating Token Index: 49

Text #18

Max Range: 4.3678. Min Range: -4.3678

Max Act: 4.0901. Min Act: -0.1700

Data Index: 5581657 (Open Web Text)

Max Activating Token Index: 821

Text #19

Max Range: 4.3678. Min Range: -4.3678

Max Act: 4.0776. Min Act: -0.1700

Data Index: 1878111 (Open Web Text)

Max Activating Token Index: 31