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

Dataset: Open Web Text

Neuron 3054 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: 1.3893. Min Range: -1.3893

Max Act: 1.3893. Min Act: -0.1696

Data Index: 8146232 (Open Web Text)

Max Activating Token Index: 25

Text #1

Max Range: 1.3893. Min Range: -1.3893

Max Act: 1.3613. Min Act: -0.1687

Data Index: 6682831 (Open Web Text)

Max Activating Token Index: 261

Text #2

Max Range: 1.3893. Min Range: -1.3893

Max Act: 1.3475. Min Act: -0.1700

Data Index: 691239 (Open Web Text)

Max Activating Token Index: 551

Text #3

Max Range: 1.3893. Min Range: -1.3893

Max Act: 1.3221. Min Act: -0.1700

Data Index: 3346152 (Open Web Text)

Max Activating Token Index: 835

Text #4

Max Range: 1.3893. Min Range: -1.3893

Max Act: 1.3225. Min Act: -0.1675

Data Index: 3846388 (Open Web Text)

Max Activating Token Index: 830

Text #5

Max Range: 1.3893. Min Range: -1.3893

Max Act: 1.3235. Min Act: -0.1422

Data Index: 1850509 (Open Web Text)

Max Activating Token Index: 85

Text #6

Max Range: 1.3893. Min Range: -1.3893

Max Act: 1.3095. Min Act: -0.1673

Data Index: 3251486 (Open Web Text)

Max Activating Token Index: 643

Text #7

Max Range: 1.3893. Min Range: -1.3893

Max Act: 1.3127. Min Act: -0.1700

Data Index: 183776 (Open Web Text)

Max Activating Token Index: 55

Text #8

Max Range: 1.3893. Min Range: -1.3893

Max Act: 1.3046. Min Act: -0.1699

Data Index: 8527545 (Open Web Text)

Max Activating Token Index: 537

Text #9

Max Range: 1.3893. Min Range: -1.3893

Max Act: 1.3128. Min Act: -0.1700

Data Index: 6996892 (Open Web Text)

Max Activating Token Index: 554

Text #10

Max Range: 1.3893. Min Range: -1.3893

Max Act: 1.2990. Min Act: -0.1700

Data Index: 6139949 (Open Web Text)

Max Activating Token Index: 700

Text #11

Max Range: 1.3893. Min Range: -1.3893

Max Act: 1.2880. Min Act: -0.1700

Data Index: 8527546 (Open Web Text)

Max Activating Token Index: 684

Text #12

Max Range: 1.3893. Min Range: -1.3893

Max Act: 1.2868. Min Act: -0.1698

Data Index: 6481298 (Open Web Text)

Max Activating Token Index: 555

Text #13

Max Range: 1.3893. Min Range: -1.3893

Max Act: 1.2766. Min Act: -0.1649

Data Index: 1850505 (Open Web Text)

Max Activating Token Index: 377

Text #14

Max Range: 1.3893. Min Range: -1.3893

Max Act: 1.2833. Min Act: -0.1700

Data Index: 7247029 (Open Web Text)

Max Activating Token Index: 186

Text #15

Max Range: 1.3893. Min Range: -1.3893

Max Act: 1.2779. Min Act: -0.1690

Data Index: 6526460 (Open Web Text)

Max Activating Token Index: 112

Text #16

Max Range: 1.3893. Min Range: -1.3893

Max Act: 1.2754. Min Act: -0.1687

Data Index: 8776869 (Open Web Text)

Max Activating Token Index: 211

Text #17

Max Range: 1.3893. Min Range: -1.3893

Max Act: 1.2722. Min Act: -0.1700

Data Index: 6079884 (Open Web Text)

Max Activating Token Index: 723

Text #18

Max Range: 1.3893. Min Range: -1.3893

Max Act: 1.2685. Min Act: -0.1700

Data Index: 2187305 (Open Web Text)

Max Activating Token Index: 378

Text #19

Max Range: 1.3893. Min Range: -1.3893

Max Act: 1.2638. Min Act: -0.1688

Data Index: 8392180 (Open Web Text)

Max Activating Token Index: 17