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

Dataset: Open Web Text

Neuron 1355 in Layer 1

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: 1.4513. Min Range: -1.4513

Max Act: 1.4491. Min Act: -0.1699

Data Index: 4046351 (Open Web Text)

Max Activating Token Index: 406

Text #1

Max Range: 1.4513. Min Range: -1.4513

Max Act: 1.4513. Min Act: -0.1700

Data Index: 331954 (Open Web Text)

Max Activating Token Index: 54

Text #2

Max Range: 1.4513. Min Range: -1.4513

Max Act: 1.4415. Min Act: -0.1700

Data Index: 8622063 (Open Web Text)

Max Activating Token Index: 204

Text #3

Max Range: 1.4513. Min Range: -1.4513

Max Act: 1.4123. Min Act: -0.1695

Data Index: 6772462 (Open Web Text)

Max Activating Token Index: 79

Text #4

Max Range: 1.4513. Min Range: -1.4513

Max Act: 1.4160. Min Act: -0.1697

Data Index: 7280003 (Open Web Text)

Max Activating Token Index: 311

Text #5

Max Range: 1.4513. Min Range: -1.4513

Max Act: 1.4129. Min Act: -0.1700

Data Index: 8283290 (Open Web Text)

Max Activating Token Index: 579

Text #6

Max Range: 1.4513. Min Range: -1.4513

Max Act: 1.4170. Min Act: -0.1700

Data Index: 5037961 (Open Web Text)

Max Activating Token Index: 399

Text #7

Max Range: 1.4513. Min Range: -1.4513

Max Act: 1.4060. Min Act: -0.1700

Data Index: 5598335 (Open Web Text)

Max Activating Token Index: 652

Text #8

Max Range: 1.4513. Min Range: -1.4513

Max Act: 1.4126. Min Act: -0.1700

Data Index: 6310705 (Open Web Text)

Max Activating Token Index: 300

Text #9

Max Range: 1.4513. Min Range: -1.4513

Max Act: 1.4049. Min Act: -0.1700

Data Index: 432595 (Open Web Text)

Max Activating Token Index: 198

Text #10

Max Range: 1.4513. Min Range: -1.4513

Max Act: 1.4014. Min Act: -0.1700

Data Index: 3036841 (Open Web Text)

Max Activating Token Index: 12

Text #11

Max Range: 1.4513. Min Range: -1.4513

Max Act: 1.3979. Min Act: -0.1700

Data Index: 6233265 (Open Web Text)

Max Activating Token Index: 6

Text #12

Max Range: 1.4513. Min Range: -1.4513

Max Act: 1.3886. Min Act: -0.1700

Data Index: 424575 (Open Web Text)

Max Activating Token Index: 21

Text #13

Max Range: 1.4513. Min Range: -1.4513

Max Act: 1.3917. Min Act: -0.1699

Data Index: 7000464 (Open Web Text)

Max Activating Token Index: 830

Text #14

Max Range: 1.4513. Min Range: -1.4513

Max Act: 1.3837. Min Act: -0.1700

Data Index: 7923705 (Open Web Text)

Max Activating Token Index: 5

Text #15

Max Range: 1.4513. Min Range: -1.4513

Max Act: 1.3929. Min Act: -0.1699

Data Index: 184096 (Open Web Text)

Max Activating Token Index: 474

Text #16

Max Range: 1.4513. Min Range: -1.4513

Max Act: 1.3889. Min Act: -0.1700

Data Index: 3177353 (Open Web Text)

Max Activating Token Index: 928

Text #17

Max Range: 1.4513. Min Range: -1.4513

Max Act: 1.3847. Min Act: -0.1700

Data Index: 7620712 (Open Web Text)

Max Activating Token Index: 485

Text #18

Max Range: 1.4513. Min Range: -1.4513

Max Act: 1.3807. Min Act: -0.1700

Data Index: 1664510 (Open Web Text)

Max Activating Token Index: 725

Text #19

Max Range: 1.4513. Min Range: -1.4513

Max Act: 1.3893. Min Act: -0.1700

Data Index: 8597811 (Open Web Text)

Max Activating Token Index: 46