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

Dataset: Open Web Text

Neuron 3040 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: 4.2730. Min Range: -4.2730

Max Act: 4.2730. Min Act: -0.1700

Data Index: 7691383 (Open Web Text)

Max Activating Token Index: 53

Text #1

Max Range: 4.2730. Min Range: -4.2730

Max Act: 4.2321. Min Act: -0.1700

Data Index: 5722085 (Open Web Text)

Max Activating Token Index: 454

Text #2

Max Range: 4.2730. Min Range: -4.2730

Max Act: 4.2251. Min Act: -0.1700

Data Index: 4620546 (Open Web Text)

Max Activating Token Index: 623

Text #3

Max Range: 4.2730. Min Range: -4.2730

Max Act: 4.2234. Min Act: -0.1700

Data Index: 663427 (Open Web Text)

Max Activating Token Index: 181

Text #4

Max Range: 4.2730. Min Range: -4.2730

Max Act: 4.1971. Min Act: -0.1700

Data Index: 1389101 (Open Web Text)

Max Activating Token Index: 768

Text #5

Max Range: 4.2730. Min Range: -4.2730

Max Act: 4.1883. Min Act: -0.1700

Data Index: 7559427 (Open Web Text)

Max Activating Token Index: 486

Text #6

Max Range: 4.2730. Min Range: -4.2730

Max Act: 4.1611. Min Act: -0.1700

Data Index: 7367437 (Open Web Text)

Max Activating Token Index: 47

Text #7

Max Range: 4.2730. Min Range: -4.2730

Max Act: 4.1795. Min Act: -0.1700

Data Index: 8624663 (Open Web Text)

Max Activating Token Index: 625

Text #8

Max Range: 4.2730. Min Range: -4.2730

Max Act: 4.1332. Min Act: -0.1700

Data Index: 3543973 (Open Web Text)

Max Activating Token Index: 863

Text #9

Max Range: 4.2730. Min Range: -4.2730

Max Act: 4.1536. Min Act: -0.1700

Data Index: 1069415 (Open Web Text)

Max Activating Token Index: 345

Text #10

Max Range: 4.2730. Min Range: -4.2730

Max Act: 4.1950. Min Act: -0.1700

Data Index: 1445827 (Open Web Text)

Max Activating Token Index: 357

Text #11

Max Range: 4.2730. Min Range: -4.2730

Max Act: 4.1563. Min Act: -0.1700

Data Index: 6493030 (Open Web Text)

Max Activating Token Index: 471

Text #12

Max Range: 4.2730. Min Range: -4.2730

Max Act: 4.1276. Min Act: -0.1700

Data Index: 1067551 (Open Web Text)

Max Activating Token Index: 117

Text #13

Max Range: 4.2730. Min Range: -4.2730

Max Act: 4.1256. Min Act: -0.1700

Data Index: 3373909 (Open Web Text)

Max Activating Token Index: 46

Text #14

Max Range: 4.2730. Min Range: -4.2730

Max Act: 4.1222. Min Act: -0.1700

Data Index: 8127895 (Open Web Text)

Max Activating Token Index: 225

Text #15

Max Range: 4.2730. Min Range: -4.2730

Max Act: 4.1063. Min Act: -0.1700

Data Index: 6168201 (Open Web Text)

Max Activating Token Index: 937

Text #16

Max Range: 4.2730. Min Range: -4.2730

Max Act: 4.1272. Min Act: -0.1700

Data Index: 696566 (Open Web Text)

Max Activating Token Index: 794

Text #17

Max Range: 4.2730. Min Range: -4.2730

Max Act: 4.1542. Min Act: -0.1700

Data Index: 290372 (Open Web Text)

Max Activating Token Index: 997

Text #18

Max Range: 4.2730. Min Range: -4.2730

Max Act: 4.1402. Min Act: -0.1700

Data Index: 1233139 (Open Web Text)

Max Activating Token Index: 385

Text #19

Max Range: 4.2730. Min Range: -4.2730

Max Act: 4.1269. Min Act: -0.1700

Data Index: 5258247 (Open Web Text)

Max Activating Token Index: 554