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

Dataset: Open Web Text

Neuron 2395 in Layer 4

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: 3.3143. Min Range: -3.3143

Max Act: 3.3143. Min Act: -0.1700

Data Index: 5618538 (Open Web Text)

Max Activating Token Index: 726

Text #1

Max Range: 3.3143. Min Range: -3.3143

Max Act: 3.1411. Min Act: -0.1700

Data Index: 5632643 (Open Web Text)

Max Activating Token Index: 120

Text #2

Max Range: 3.3143. Min Range: -3.3143

Max Act: 3.1221. Min Act: -0.1700

Data Index: 4174725 (Open Web Text)

Max Activating Token Index: 832

Text #3

Max Range: 3.3143. Min Range: -3.3143

Max Act: 3.1019. Min Act: -0.1700

Data Index: 2722276 (Open Web Text)

Max Activating Token Index: 126

Text #4

Max Range: 3.3143. Min Range: -3.3143

Max Act: 3.0855. Min Act: -0.1700

Data Index: 5338048 (Open Web Text)

Max Activating Token Index: 946

Text #5

Max Range: 3.3143. Min Range: -3.3143

Max Act: 3.0788. Min Act: -0.1700

Data Index: 3349472 (Open Web Text)

Max Activating Token Index: 585

Text #6

Max Range: 3.3143. Min Range: -3.3143

Max Act: 3.0717. Min Act: -0.1700

Data Index: 907322 (Open Web Text)

Max Activating Token Index: 963

Text #7

Max Range: 3.3143. Min Range: -3.3143

Max Act: 3.0481. Min Act: -0.1700

Data Index: 3260888 (Open Web Text)

Max Activating Token Index: 514

Text #8

Max Range: 3.3143. Min Range: -3.3143

Max Act: 3.0331. Min Act: -0.1700

Data Index: 8148820 (Open Web Text)

Max Activating Token Index: 725

Text #9

Max Range: 3.3143. Min Range: -3.3143

Max Act: 3.0192. Min Act: -0.1700

Data Index: 836094 (Open Web Text)

Max Activating Token Index: 719

Text #10

Max Range: 3.3143. Min Range: -3.3143

Max Act: 3.0085. Min Act: -0.1700

Data Index: 8678821 (Open Web Text)

Max Activating Token Index: 638

Text #11

Max Range: 3.3143. Min Range: -3.3143

Max Act: 3.0033. Min Act: -0.1700

Data Index: 4022884 (Open Web Text)

Max Activating Token Index: 534

Text #12

Max Range: 3.3143. Min Range: -3.3143

Max Act: 3.0058. Min Act: -0.1700

Data Index: 5871997 (Open Web Text)

Max Activating Token Index: 804

Text #13

Max Range: 3.3143. Min Range: -3.3143

Max Act: 3.0106. Min Act: -0.1700

Data Index: 5872009 (Open Web Text)

Max Activating Token Index: 465

Text #14

Max Range: 3.3143. Min Range: -3.3143

Max Act: 2.9850. Min Act: -0.1700

Data Index: 8624098 (Open Web Text)

Max Activating Token Index: 888

Text #15

Max Range: 3.3143. Min Range: -3.3143

Max Act: 3.0044. Min Act: -0.1700

Data Index: 6597918 (Open Web Text)

Max Activating Token Index: 602

Text #16

Max Range: 3.3143. Min Range: -3.3143

Max Act: 2.9935. Min Act: -0.1700

Data Index: 5872013 (Open Web Text)

Max Activating Token Index: 487

Text #17

Max Range: 3.3143. Min Range: -3.3143

Max Act: 2.9745. Min Act: -0.1700

Data Index: 2889608 (Open Web Text)

Max Activating Token Index: 327

Text #18

Max Range: 3.3143. Min Range: -3.3143

Max Act: 2.9660. Min Act: -0.1700

Data Index: 18344 (Open Web Text)

Max Activating Token Index: 750

Text #19

Max Range: 3.3143. Min Range: -3.3143

Max Act: 2.9281. Min Act: -0.1700

Data Index: 1607130 (Open Web Text)

Max Activating Token Index: 735