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

Dataset: Open Web Text

Neuron 8 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: 2.1582. Min Range: -2.1582

Max Act: 2.1582. Min Act: -0.1700

Data Index: 298944 (Open Web Text)

Max Activating Token Index: 553

Text #1

Max Range: 2.1582. Min Range: -2.1582

Max Act: 2.0492. Min Act: -0.1700

Data Index: 1163117 (Open Web Text)

Max Activating Token Index: 506

Text #2

Max Range: 2.1582. Min Range: -2.1582

Max Act: 2.0441. Min Act: -0.1700

Data Index: 4285332 (Open Web Text)

Max Activating Token Index: 549

Text #3

Max Range: 2.1582. Min Range: -2.1582

Max Act: 2.0093. Min Act: -0.1700

Data Index: 2383033 (Open Web Text)

Max Activating Token Index: 696

Text #4

Max Range: 2.1582. Min Range: -2.1582

Max Act: 1.9905. Min Act: -0.1700

Data Index: 7566480 (Open Web Text)

Max Activating Token Index: 549

Text #5

Max Range: 2.1582. Min Range: -2.1582

Max Act: 1.9613. Min Act: -0.1700

Data Index: 8230521 (Open Web Text)

Max Activating Token Index: 42

Text #6

Max Range: 2.1582. Min Range: -2.1582

Max Act: 1.9778. Min Act: -0.1700

Data Index: 7827987 (Open Web Text)

Max Activating Token Index: 6

Text #7

Max Range: 2.1582. Min Range: -2.1582

Max Act: 1.9704. Min Act: -0.1700

Data Index: 6376232 (Open Web Text)

Max Activating Token Index: 984

Text #8

Max Range: 2.1582. Min Range: -2.1582

Max Act: 1.9431. Min Act: -0.1700

Data Index: 4134708 (Open Web Text)

Max Activating Token Index: 795

Text #9

Max Range: 2.1582. Min Range: -2.1582

Max Act: 1.9374. Min Act: -0.1700

Data Index: 1236141 (Open Web Text)

Max Activating Token Index: 14

Text #10

Max Range: 2.1582. Min Range: -2.1582

Max Act: 1.9350. Min Act: -0.1700

Data Index: 843330 (Open Web Text)

Max Activating Token Index: 605

Text #11

Max Range: 2.1582. Min Range: -2.1582

Max Act: 1.9362. Min Act: -0.1700

Data Index: 5439958 (Open Web Text)

Max Activating Token Index: 14

Text #12

Max Range: 2.1582. Min Range: -2.1582

Max Act: 1.9332. Min Act: -0.1700

Data Index: 8809428 (Open Web Text)

Max Activating Token Index: 842

Text #13

Max Range: 2.1582. Min Range: -2.1582

Max Act: 1.9306. Min Act: -0.1700

Data Index: 4777223 (Open Web Text)

Max Activating Token Index: 439

Text #14

Max Range: 2.1582. Min Range: -2.1582

Max Act: 1.9206. Min Act: -0.1700

Data Index: 3318011 (Open Web Text)

Max Activating Token Index: 20

Text #15

Max Range: 2.1582. Min Range: -2.1582

Max Act: 1.9466. Min Act: -0.1700

Data Index: 5622568 (Open Web Text)

Max Activating Token Index: 565

Text #16

Max Range: 2.1582. Min Range: -2.1582

Max Act: 1.9250. Min Act: -0.1700

Data Index: 1962747 (Open Web Text)

Max Activating Token Index: 492

Text #17

Max Range: 2.1582. Min Range: -2.1582

Max Act: 1.9030. Min Act: -0.1700

Data Index: 4437711 (Open Web Text)

Max Activating Token Index: 220

Text #18

Max Range: 2.1582. Min Range: -2.1582

Max Act: 1.9261. Min Act: -0.1700

Data Index: 3389635 (Open Web Text)

Max Activating Token Index: 573

Text #19

Max Range: 2.1582. Min Range: -2.1582

Max Act: 1.9038. Min Act: -0.1700

Data Index: 7114394 (Open Web Text)

Max Activating Token Index: 365