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

Dataset: Open Web Text

Neuron 1405 in Layer 6

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: 3.8947. Min Range: -3.8947

Max Act: 3.8947. Min Act: -0.1700

Data Index: 7488173 (Open Web Text)

Max Activating Token Index: 95

Text #1

Max Range: 3.8947. Min Range: -3.8947

Max Act: 3.8521. Min Act: -0.1700

Data Index: 2869633 (Open Web Text)

Max Activating Token Index: 568

Text #2

Max Range: 3.8947. Min Range: -3.8947

Max Act: 3.7717. Min Act: -0.1700

Data Index: 2210843 (Open Web Text)

Max Activating Token Index: 557

Text #3

Max Range: 3.8947. Min Range: -3.8947

Max Act: 3.7858. Min Act: -0.1700

Data Index: 6926874 (Open Web Text)

Max Activating Token Index: 166

Text #4

Max Range: 3.8947. Min Range: -3.8947

Max Act: 3.7333. Min Act: -0.1700

Data Index: 9682 (Open Web Text)

Max Activating Token Index: 461

Text #5

Max Range: 3.8947. Min Range: -3.8947

Max Act: 3.7640. Min Act: -0.1700

Data Index: 6160687 (Open Web Text)

Max Activating Token Index: 801

Text #6

Max Range: 3.8947. Min Range: -3.8947

Max Act: 3.7141. Min Act: -0.1700

Data Index: 2320181 (Open Web Text)

Max Activating Token Index: 943

Text #7

Max Range: 3.8947. Min Range: -3.8947

Max Act: 3.7408. Min Act: -0.1700

Data Index: 3338648 (Open Web Text)

Max Activating Token Index: 67

Text #8

Max Range: 3.8947. Min Range: -3.8947

Max Act: 3.6912. Min Act: -0.1700

Data Index: 1538467 (Open Web Text)

Max Activating Token Index: 510

Text #9

Max Range: 3.8947. Min Range: -3.8947

Max Act: 3.6908. Min Act: -0.1700

Data Index: 4545144 (Open Web Text)

Max Activating Token Index: 932

Text #10

Max Range: 3.8947. Min Range: -3.8947

Max Act: 3.6943. Min Act: -0.1700

Data Index: 4473178 (Open Web Text)

Max Activating Token Index: 656

Text #11

Max Range: 3.8947. Min Range: -3.8947

Max Act: 3.6573. Min Act: -0.1700

Data Index: 6351006 (Open Web Text)

Max Activating Token Index: 753

Text #12

Max Range: 3.8947. Min Range: -3.8947

Max Act: 3.6681. Min Act: -0.1700

Data Index: 552511 (Open Web Text)

Max Activating Token Index: 784

Text #13

Max Range: 3.8947. Min Range: -3.8947

Max Act: 3.6763. Min Act: -0.1700

Data Index: 24572 (Open Web Text)

Max Activating Token Index: 468

Text #14

Max Range: 3.8947. Min Range: -3.8947

Max Act: 3.6480. Min Act: -0.1700

Data Index: 2593661 (Open Web Text)

Max Activating Token Index: 26

Text #15

Max Range: 3.8947. Min Range: -3.8947

Max Act: 3.6561. Min Act: -0.1700

Data Index: 7513448 (Open Web Text)

Max Activating Token Index: 297

Text #16

Max Range: 3.8947. Min Range: -3.8947

Max Act: 3.6255. Min Act: -0.1700

Data Index: 3679483 (Open Web Text)

Max Activating Token Index: 183

Text #17

Max Range: 3.8947. Min Range: -3.8947

Max Act: 3.6367. Min Act: -0.1700

Data Index: 5926365 (Open Web Text)

Max Activating Token Index: 54

Text #18

Max Range: 3.8947. Min Range: -3.8947

Max Act: 3.6309. Min Act: -0.1700

Data Index: 1947778 (Open Web Text)

Max Activating Token Index: 324

Text #19

Max Range: 3.8947. Min Range: -3.8947

Max Act: 3.6338. Min Act: -0.1700

Data Index: 1686501 (Open Web Text)

Max Activating Token Index: 976