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

Dataset: Open Web Text

Neuron 2800 in Layer 2

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: 2.3039. Min Range: -2.3039

Max Act: 2.3039. Min Act: -0.1700

Data Index: 2034703 (Open Web Text)

Max Activating Token Index: 563

Text #1

Max Range: 2.3039. Min Range: -2.3039

Max Act: 2.2609. Min Act: -0.1700

Data Index: 3333634 (Open Web Text)

Max Activating Token Index: 676

Text #2

Max Range: 2.3039. Min Range: -2.3039

Max Act: 2.2596. Min Act: -0.1700

Data Index: 1250077 (Open Web Text)

Max Activating Token Index: 20

Text #3

Max Range: 2.3039. Min Range: -2.3039

Max Act: 2.2431. Min Act: -0.1700

Data Index: 8281417 (Open Web Text)

Max Activating Token Index: 222

Text #4

Max Range: 2.3039. Min Range: -2.3039

Max Act: 2.2282. Min Act: -0.1699

Data Index: 8091020 (Open Web Text)

Max Activating Token Index: 654

Text #5

Max Range: 2.3039. Min Range: -2.3039

Max Act: 2.2392. Min Act: -0.1700

Data Index: 5656838 (Open Web Text)

Max Activating Token Index: 943

Text #6

Max Range: 2.3039. Min Range: -2.3039

Max Act: 2.2300. Min Act: -0.1700

Data Index: 143856 (Open Web Text)

Max Activating Token Index: 496

Text #7

Max Range: 2.3039. Min Range: -2.3039

Max Act: 2.2149. Min Act: -0.1700

Data Index: 6249816 (Open Web Text)

Max Activating Token Index: 299

Text #8

Max Range: 2.3039. Min Range: -2.3039

Max Act: 2.2001. Min Act: -0.1700

Data Index: 5271790 (Open Web Text)

Max Activating Token Index: 349

Text #9

Max Range: 2.3039. Min Range: -2.3039

Max Act: 2.1852. Min Act: -0.1700

Data Index: 5541344 (Open Web Text)

Max Activating Token Index: 248

Text #10

Max Range: 2.3039. Min Range: -2.3039

Max Act: 2.1783. Min Act: -0.1700

Data Index: 4689088 (Open Web Text)

Max Activating Token Index: 492

Text #11

Max Range: 2.3039. Min Range: -2.3039

Max Act: 2.1765. Min Act: -0.1700

Data Index: 729706 (Open Web Text)

Max Activating Token Index: 147

Text #12

Max Range: 2.3039. Min Range: -2.3039

Max Act: 2.1728. Min Act: -0.1700

Data Index: 6624218 (Open Web Text)

Max Activating Token Index: 825

Text #13

Max Range: 2.3039. Min Range: -2.3039

Max Act: 2.1615. Min Act: -0.1700

Data Index: 4347674 (Open Web Text)

Max Activating Token Index: 241

Text #14

Max Range: 2.3039. Min Range: -2.3039

Max Act: 2.1763. Min Act: -0.1700

Data Index: 5865746 (Open Web Text)

Max Activating Token Index: 67

Text #15

Max Range: 2.3039. Min Range: -2.3039

Max Act: 2.1591. Min Act: -0.1700

Data Index: 5928742 (Open Web Text)

Max Activating Token Index: 166

Text #16

Max Range: 2.3039. Min Range: -2.3039

Max Act: 2.1610. Min Act: -0.1691

Data Index: 5928743 (Open Web Text)

Max Activating Token Index: 783

Text #17

Max Range: 2.3039. Min Range: -2.3039

Max Act: 2.1384. Min Act: -0.1697

Data Index: 3455106 (Open Web Text)

Max Activating Token Index: 247

Text #18

Max Range: 2.3039. Min Range: -2.3039

Max Act: 2.1557. Min Act: -0.1700

Data Index: 6797356 (Open Web Text)

Max Activating Token Index: 706

Text #19

Max Range: 2.3039. Min Range: -2.3039

Max Act: 2.1421. Min Act: -0.1698

Data Index: 7552481 (Open Web Text)

Max Activating Token Index: 233