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

Dataset: Open Web Text

Neuron 2675 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: 3.1101. Min Range: -3.1101

Max Act: 3.1101. Min Act: -0.1700

Data Index: 10657 (Open Web Text)

Max Activating Token Index: 58

Text #1

Max Range: 3.1101. Min Range: -3.1101

Max Act: 3.0298. Min Act: -0.1700

Data Index: 2743214 (Open Web Text)

Max Activating Token Index: 581

Text #2

Max Range: 3.1101. Min Range: -3.1101

Max Act: 3.0208. Min Act: -0.1700

Data Index: 2532221 (Open Web Text)

Max Activating Token Index: 20

Text #3

Max Range: 3.1101. Min Range: -3.1101

Max Act: 2.9771. Min Act: -0.1700

Data Index: 3053416 (Open Web Text)

Max Activating Token Index: 257

Text #4

Max Range: 3.1101. Min Range: -3.1101

Max Act: 2.9660. Min Act: -0.1700

Data Index: 2159545 (Open Web Text)

Max Activating Token Index: 154

Text #5

Max Range: 3.1101. Min Range: -3.1101

Max Act: 2.9709. Min Act: -0.1700

Data Index: 7737963 (Open Web Text)

Max Activating Token Index: 43

Text #6

Max Range: 3.1101. Min Range: -3.1101

Max Act: 2.9547. Min Act: -0.1700

Data Index: 4949774 (Open Web Text)

Max Activating Token Index: 51

Text #7

Max Range: 3.1101. Min Range: -3.1101

Max Act: 2.9063. Min Act: -0.1700

Data Index: 6788417 (Open Web Text)

Max Activating Token Index: 193

Text #8

Max Range: 3.1101. Min Range: -3.1101

Max Act: 2.9079. Min Act: -0.1700

Data Index: 6513032 (Open Web Text)

Max Activating Token Index: 58

Text #9

Max Range: 3.1101. Min Range: -3.1101

Max Act: 2.8873. Min Act: -0.1700

Data Index: 3307665 (Open Web Text)

Max Activating Token Index: 97

Text #10

Max Range: 3.1101. Min Range: -3.1101

Max Act: 2.9043. Min Act: -0.1700

Data Index: 7302333 (Open Web Text)

Max Activating Token Index: 890

Text #11

Max Range: 3.1101. Min Range: -3.1101

Max Act: 2.8711. Min Act: -0.1700

Data Index: 4456591 (Open Web Text)

Max Activating Token Index: 242

Text #12

Max Range: 3.1101. Min Range: -3.1101

Max Act: 2.8814. Min Act: -0.1700

Data Index: 6751963 (Open Web Text)

Max Activating Token Index: 24

Text #13

Max Range: 3.1101. Min Range: -3.1101

Max Act: 2.8463. Min Act: -0.1700

Data Index: 7746765 (Open Web Text)

Max Activating Token Index: 643

Text #14

Max Range: 3.1101. Min Range: -3.1101

Max Act: 2.8736. Min Act: -0.1700

Data Index: 1302301 (Open Web Text)

Max Activating Token Index: 538

Text #15

Max Range: 3.1101. Min Range: -3.1101

Max Act: 2.8514. Min Act: -0.1700

Data Index: 2743449 (Open Web Text)

Max Activating Token Index: 23

Text #16

Max Range: 3.1101. Min Range: -3.1101

Max Act: 2.8332. Min Act: -0.1700

Data Index: 4786033 (Open Web Text)

Max Activating Token Index: 446

Text #17

Max Range: 3.1101. Min Range: -3.1101

Max Act: 2.8421. Min Act: -0.1700

Data Index: 2966560 (Open Web Text)

Max Activating Token Index: 616

Text #18

Max Range: 3.1101. Min Range: -3.1101

Max Act: 2.8389. Min Act: -0.1700

Data Index: 5312208 (Open Web Text)

Max Activating Token Index: 27

Text #19

Max Range: 3.1101. Min Range: -3.1101

Max Act: 2.8403. Min Act: -0.1700

Data Index: 580927 (Open Web Text)

Max Activating Token Index: 33