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

Dataset: Open Web Text

Neuron 1559 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: 3.1674. Min Range: -3.1674

Max Act: 3.1674. Min Act: -0.1700

Data Index: 2862422 (Open Web Text)

Max Activating Token Index: 815

Text #1

Max Range: 3.1674. Min Range: -3.1674

Max Act: 3.1091. Min Act: -0.1700

Data Index: 1264368 (Open Web Text)

Max Activating Token Index: 198

Text #2

Max Range: 3.1674. Min Range: -3.1674

Max Act: 3.1124. Min Act: -0.1700

Data Index: 6636267 (Open Web Text)

Max Activating Token Index: 636

Text #3

Max Range: 3.1674. Min Range: -3.1674

Max Act: 3.0735. Min Act: -0.1700

Data Index: 1959043 (Open Web Text)

Max Activating Token Index: 372

Text #4

Max Range: 3.1674. Min Range: -3.1674

Max Act: 3.0651. Min Act: -0.1700

Data Index: 2254646 (Open Web Text)

Max Activating Token Index: 868

Text #5

Max Range: 3.1674. Min Range: -3.1674

Max Act: 3.0563. Min Act: -0.1700

Data Index: 6076405 (Open Web Text)

Max Activating Token Index: 14

Text #6

Max Range: 3.1674. Min Range: -3.1674

Max Act: 3.0467. Min Act: -0.1700

Data Index: 390545 (Open Web Text)

Max Activating Token Index: 906

Text #7

Max Range: 3.1674. Min Range: -3.1674

Max Act: 3.0490. Min Act: -0.1700

Data Index: 4637331 (Open Web Text)

Max Activating Token Index: 642

Text #8

Max Range: 3.1674. Min Range: -3.1674

Max Act: 3.0112. Min Act: -0.1700

Data Index: 6245741 (Open Web Text)

Max Activating Token Index: 6

Text #9

Max Range: 3.1674. Min Range: -3.1674

Max Act: 3.0220. Min Act: -0.1700

Data Index: 7607858 (Open Web Text)

Max Activating Token Index: 481

Text #10

Max Range: 3.1674. Min Range: -3.1674

Max Act: 3.0004. Min Act: -0.1700

Data Index: 5677980 (Open Web Text)

Max Activating Token Index: 90

Text #11

Max Range: 3.1674. Min Range: -3.1674

Max Act: 2.9840. Min Act: -0.1700

Data Index: 270733 (Open Web Text)

Max Activating Token Index: 518

Text #12

Max Range: 3.1674. Min Range: -3.1674

Max Act: 2.9786. Min Act: -0.1700

Data Index: 1544147 (Open Web Text)

Max Activating Token Index: 303

Text #13

Max Range: 3.1674. Min Range: -3.1674

Max Act: 2.9785. Min Act: -0.1700

Data Index: 7804512 (Open Web Text)

Max Activating Token Index: 385

Text #14

Max Range: 3.1674. Min Range: -3.1674

Max Act: 2.9599. Min Act: -0.1700

Data Index: 897869 (Open Web Text)

Max Activating Token Index: 634

Text #15

Max Range: 3.1674. Min Range: -3.1674

Max Act: 2.9153. Min Act: -0.1700

Data Index: 5626884 (Open Web Text)

Max Activating Token Index: 163

Text #16

Max Range: 3.1674. Min Range: -3.1674

Max Act: 2.9712. Min Act: -0.1700

Data Index: 5713045 (Open Web Text)

Max Activating Token Index: 409

Text #17

Max Range: 3.1674. Min Range: -3.1674

Max Act: 2.9496. Min Act: -0.1700

Data Index: 1927060 (Open Web Text)

Max Activating Token Index: 552

Text #18

Max Range: 3.1674. Min Range: -3.1674

Max Act: 2.9597. Min Act: -0.1700

Data Index: 6806122 (Open Web Text)

Max Activating Token Index: 428

Text #19

Max Range: 3.1674. Min Range: -3.1674

Max Act: 2.9533. Min Act: -0.1700

Data Index: 2429842 (Open Web Text)

Max Activating Token Index: 511