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

Dataset: Open Web Text

Neuron 2250 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: 5.4407. Min Range: -5.4407

Max Act: 5.4407. Min Act: -0.1700

Data Index: 841344 (Open Web Text)

Max Activating Token Index: 658

Text #1

Max Range: 5.4407. Min Range: -5.4407

Max Act: 5.2065. Min Act: -0.1700

Data Index: 1988138 (Open Web Text)

Max Activating Token Index: 686

Text #2

Max Range: 5.4407. Min Range: -5.4407

Max Act: 5.2030. Min Act: -0.1700

Data Index: 4072644 (Open Web Text)

Max Activating Token Index: 660

Text #3

Max Range: 5.4407. Min Range: -5.4407

Max Act: 5.1797. Min Act: -0.1700

Data Index: 7108436 (Open Web Text)

Max Activating Token Index: 720

Text #4

Max Range: 5.4407. Min Range: -5.4407

Max Act: 5.1690. Min Act: -0.1700

Data Index: 7564034 (Open Web Text)

Max Activating Token Index: 276

Text #5

Max Range: 5.4407. Min Range: -5.4407

Max Act: 5.1414. Min Act: -0.1700

Data Index: 5093180 (Open Web Text)

Max Activating Token Index: 72

Text #6

Max Range: 5.4407. Min Range: -5.4407

Max Act: 5.1274. Min Act: -0.1700

Data Index: 8051562 (Open Web Text)

Max Activating Token Index: 817

Text #7

Max Range: 5.4407. Min Range: -5.4407

Max Act: 5.1256. Min Act: -0.1700

Data Index: 2588432 (Open Web Text)

Max Activating Token Index: 49

Text #8

Max Range: 5.4407. Min Range: -5.4407

Max Act: 5.1050. Min Act: -0.1700

Data Index: 6662415 (Open Web Text)

Max Activating Token Index: 533

Text #9

Max Range: 5.4407. Min Range: -5.4407

Max Act: 5.1506. Min Act: -0.1700

Data Index: 1130460 (Open Web Text)

Max Activating Token Index: 77

Text #10

Max Range: 5.4407. Min Range: -5.4407

Max Act: 5.1095. Min Act: -0.1700

Data Index: 8289113 (Open Web Text)

Max Activating Token Index: 407

Text #11

Max Range: 5.4407. Min Range: -5.4407

Max Act: 5.1186. Min Act: -0.1700

Data Index: 6826926 (Open Web Text)

Max Activating Token Index: 957

Text #12

Max Range: 5.4407. Min Range: -5.4407

Max Act: 5.1094. Min Act: -0.1700

Data Index: 2626263 (Open Web Text)

Max Activating Token Index: 86

Text #13

Max Range: 5.4407. Min Range: -5.4407

Max Act: 5.0625. Min Act: -0.1700

Data Index: 2450719 (Open Web Text)

Max Activating Token Index: 848

Text #14

Max Range: 5.4407. Min Range: -5.4407

Max Act: 5.0512. Min Act: -0.1700

Data Index: 4901317 (Open Web Text)

Max Activating Token Index: 451

Text #15

Max Range: 5.4407. Min Range: -5.4407

Max Act: 5.0603. Min Act: -0.1700

Data Index: 1227370 (Open Web Text)

Max Activating Token Index: 71

Text #16

Max Range: 5.4407. Min Range: -5.4407

Max Act: 5.0745. Min Act: -0.1700

Data Index: 5168719 (Open Web Text)

Max Activating Token Index: 675

Text #17

Max Range: 5.4407. Min Range: -5.4407

Max Act: 5.0645. Min Act: -0.1700

Data Index: 6798834 (Open Web Text)

Max Activating Token Index: 420

Text #18

Max Range: 5.4407. Min Range: -5.4407

Max Act: 5.0445. Min Act: -0.1700

Data Index: 3140973 (Open Web Text)

Max Activating Token Index: 191

Text #19

Max Range: 5.4407. Min Range: -5.4407

Max Act: 5.0306. Min Act: -0.1700

Data Index: 4905589 (Open Web Text)

Max Activating Token Index: 689