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

Dataset: Open Web Text

Neuron 317 in Layer 3

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: 4.8688. Min Range: -4.8688

Max Act: 4.8688. Min Act: -0.1700

Data Index: 503249 (Open Web Text)

Max Activating Token Index: 116

Text #1

Max Range: 4.8688. Min Range: -4.8688

Max Act: 4.8100. Min Act: -0.1700

Data Index: 3851489 (Open Web Text)

Max Activating Token Index: 41

Text #2

Max Range: 4.8688. Min Range: -4.8688

Max Act: 4.8667. Min Act: -0.1700

Data Index: 6165016 (Open Web Text)

Max Activating Token Index: 317

Text #3

Max Range: 4.8688. Min Range: -4.8688

Max Act: 4.7918. Min Act: -0.1700

Data Index: 5460128 (Open Web Text)

Max Activating Token Index: 57

Text #4

Max Range: 4.8688. Min Range: -4.8688

Max Act: 4.7826. Min Act: -0.1700

Data Index: 1669675 (Open Web Text)

Max Activating Token Index: 977

Text #5

Max Range: 4.8688. Min Range: -4.8688

Max Act: 4.7820. Min Act: -0.1700

Data Index: 5867350 (Open Web Text)

Max Activating Token Index: 607

Text #6

Max Range: 4.8688. Min Range: -4.8688

Max Act: 4.7569. Min Act: -0.1700

Data Index: 8082014 (Open Web Text)

Max Activating Token Index: 870

Text #7

Max Range: 4.8688. Min Range: -4.8688

Max Act: 4.7532. Min Act: -0.1700

Data Index: 6758806 (Open Web Text)

Max Activating Token Index: 1006

Text #8

Max Range: 4.8688. Min Range: -4.8688

Max Act: 4.7573. Min Act: -0.1700

Data Index: 1927951 (Open Web Text)

Max Activating Token Index: 23

Text #9

Max Range: 4.8688. Min Range: -4.8688

Max Act: 4.7678. Min Act: -0.1700

Data Index: 5192913 (Open Web Text)

Max Activating Token Index: 286

Text #10

Max Range: 4.8688. Min Range: -4.8688

Max Act: 4.7529. Min Act: -0.1700

Data Index: 6072239 (Open Web Text)

Max Activating Token Index: 112

Text #11

Max Range: 4.8688. Min Range: -4.8688

Max Act: 4.7403. Min Act: -0.1700

Data Index: 8591132 (Open Web Text)

Max Activating Token Index: 865

Text #12

Max Range: 4.8688. Min Range: -4.8688

Max Act: 4.7124. Min Act: -0.1700

Data Index: 1460188 (Open Web Text)

Max Activating Token Index: 109

Text #13

Max Range: 4.8688. Min Range: -4.8688

Max Act: 4.7539. Min Act: -0.1700

Data Index: 21697 (Open Web Text)

Max Activating Token Index: 987

Text #14

Max Range: 4.8688. Min Range: -4.8688

Max Act: 4.7248. Min Act: -0.1700

Data Index: 457154 (Open Web Text)

Max Activating Token Index: 934

Text #15

Max Range: 4.8688. Min Range: -4.8688

Max Act: 4.7050. Min Act: -0.1700

Data Index: 4103156 (Open Web Text)

Max Activating Token Index: 425

Text #16

Max Range: 4.8688. Min Range: -4.8688

Max Act: 4.7103. Min Act: -0.1700

Data Index: 1360066 (Open Web Text)

Max Activating Token Index: 519

Text #17

Max Range: 4.8688. Min Range: -4.8688

Max Act: 4.7105. Min Act: -0.1700

Data Index: 7250322 (Open Web Text)

Max Activating Token Index: 918

Text #18

Max Range: 4.8688. Min Range: -4.8688

Max Act: 4.7174. Min Act: -0.1700

Data Index: 1228893 (Open Web Text)

Max Activating Token Index: 62

Text #19

Max Range: 4.8688. Min Range: -4.8688

Max Act: 4.7464. Min Act: -0.1700

Data Index: 8075522 (Open Web Text)

Max Activating Token Index: 207