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

Dataset: Open Web Text

Neuron 2160 in Layer 5

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: 3.6697. Min Range: -3.6697

Max Act: 3.6697. Min Act: -0.1700

Data Index: 3368673 (Open Web Text)

Max Activating Token Index: 72

Text #1

Max Range: 3.6697. Min Range: -3.6697

Max Act: 3.6596. Min Act: -0.1700

Data Index: 3515696 (Open Web Text)

Max Activating Token Index: 963

Text #2

Max Range: 3.6697. Min Range: -3.6697

Max Act: 3.6183. Min Act: -0.1700

Data Index: 6758714 (Open Web Text)

Max Activating Token Index: 479

Text #3

Max Range: 3.6697. Min Range: -3.6697

Max Act: 3.6105. Min Act: -0.1700

Data Index: 356575 (Open Web Text)

Max Activating Token Index: 9

Text #4

Max Range: 3.6697. Min Range: -3.6697

Max Act: 3.5930. Min Act: -0.1700

Data Index: 222526 (Open Web Text)

Max Activating Token Index: 824

Text #5

Max Range: 3.6697. Min Range: -3.6697

Max Act: 3.5859. Min Act: -0.1700

Data Index: 1805012 (Open Web Text)

Max Activating Token Index: 468

Text #6

Max Range: 3.6697. Min Range: -3.6697

Max Act: 3.6304. Min Act: -0.1700

Data Index: 6083147 (Open Web Text)

Max Activating Token Index: 740

Text #7

Max Range: 3.6697. Min Range: -3.6697

Max Act: 3.5906. Min Act: -0.1700

Data Index: 7599371 (Open Web Text)

Max Activating Token Index: 902

Text #8

Max Range: 3.6697. Min Range: -3.6697

Max Act: 3.5859. Min Act: -0.1700

Data Index: 3526852 (Open Web Text)

Max Activating Token Index: 733

Text #9

Max Range: 3.6697. Min Range: -3.6697

Max Act: 3.6129. Min Act: -0.1700

Data Index: 6550043 (Open Web Text)

Max Activating Token Index: 230

Text #10

Max Range: 3.6697. Min Range: -3.6697

Max Act: 3.6127. Min Act: -0.1700

Data Index: 5009143 (Open Web Text)

Max Activating Token Index: 221

Text #11

Max Range: 3.6697. Min Range: -3.6697

Max Act: 3.5766. Min Act: -0.1700

Data Index: 6770189 (Open Web Text)

Max Activating Token Index: 364

Text #12

Max Range: 3.6697. Min Range: -3.6697

Max Act: 3.5528. Min Act: -0.1700

Data Index: 3859006 (Open Web Text)

Max Activating Token Index: 121

Text #13

Max Range: 3.6697. Min Range: -3.6697

Max Act: 3.5836. Min Act: -0.1700

Data Index: 2033405 (Open Web Text)

Max Activating Token Index: 336

Text #14

Max Range: 3.6697. Min Range: -3.6697

Max Act: 3.5664. Min Act: -0.1700

Data Index: 4803463 (Open Web Text)

Max Activating Token Index: 1002

Text #15

Max Range: 3.6697. Min Range: -3.6697

Max Act: 3.5687. Min Act: -0.1700

Data Index: 6572370 (Open Web Text)

Max Activating Token Index: 153

Text #16

Max Range: 3.6697. Min Range: -3.6697

Max Act: 3.5446. Min Act: -0.1700

Data Index: 7144912 (Open Web Text)

Max Activating Token Index: 659

Text #17

Max Range: 3.6697. Min Range: -3.6697

Max Act: 3.5598. Min Act: -0.1700

Data Index: 5737616 (Open Web Text)

Max Activating Token Index: 651

Text #18

Max Range: 3.6697. Min Range: -3.6697

Max Act: 3.5570. Min Act: -0.1700

Data Index: 1418414 (Open Web Text)

Max Activating Token Index: 555

Text #19

Max Range: 3.6697. Min Range: -3.6697

Max Act: 3.5299. Min Act: -0.1700

Data Index: 7431310 (Open Web Text)

Max Activating Token Index: 810