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

Dataset: Open Web Text

Neuron 2918 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: 1.8441. Min Range: -1.8441

Max Act: 1.8441. Min Act: -0.1700

Data Index: 6193588 (Open Web Text)

Max Activating Token Index: 428

Text #1

Max Range: 1.8441. Min Range: -1.8441

Max Act: 1.8416. Min Act: -0.1700

Data Index: 5835263 (Open Web Text)

Max Activating Token Index: 49

Text #2

Max Range: 1.8441. Min Range: -1.8441

Max Act: 1.8334. Min Act: -0.1696

Data Index: 6256363 (Open Web Text)

Max Activating Token Index: 568

Text #3

Max Range: 1.8441. Min Range: -1.8441

Max Act: 1.8167. Min Act: -0.1700

Data Index: 1542529 (Open Web Text)

Max Activating Token Index: 501

Text #4

Max Range: 1.8441. Min Range: -1.8441

Max Act: 1.8218. Min Act: -0.1673

Data Index: 5557247 (Open Web Text)

Max Activating Token Index: 517

Text #5

Max Range: 1.8441. Min Range: -1.8441

Max Act: 1.8224. Min Act: -0.1700

Data Index: 8099816 (Open Web Text)

Max Activating Token Index: 895

Text #6

Max Range: 1.8441. Min Range: -1.8441

Max Act: 1.8079. Min Act: -0.1697

Data Index: 6096334 (Open Web Text)

Max Activating Token Index: 935

Text #7

Max Range: 1.8441. Min Range: -1.8441

Max Act: 1.8080. Min Act: -0.1700

Data Index: 6052402 (Open Web Text)

Max Activating Token Index: 966

Text #8

Max Range: 1.8441. Min Range: -1.8441

Max Act: 1.8085. Min Act: -0.1700

Data Index: 3787218 (Open Web Text)

Max Activating Token Index: 520

Text #9

Max Range: 1.8441. Min Range: -1.8441

Max Act: 1.7977. Min Act: -0.1700

Data Index: 7874399 (Open Web Text)

Max Activating Token Index: 252

Text #10

Max Range: 1.8441. Min Range: -1.8441

Max Act: 1.7976. Min Act: -0.1700

Data Index: 6629161 (Open Web Text)

Max Activating Token Index: 964

Text #11

Max Range: 1.8441. Min Range: -1.8441

Max Act: 1.8017. Min Act: -0.1700

Data Index: 2767838 (Open Web Text)

Max Activating Token Index: 318

Text #12

Max Range: 1.8441. Min Range: -1.8441

Max Act: 1.7987. Min Act: -0.1700

Data Index: 694534 (Open Web Text)

Max Activating Token Index: 578

Text #13

Max Range: 1.8441. Min Range: -1.8441

Max Act: 1.7892. Min Act: -0.1700

Data Index: 7573221 (Open Web Text)

Max Activating Token Index: 855

Text #14

Max Range: 1.8441. Min Range: -1.8441

Max Act: 1.7930. Min Act: -0.1700

Data Index: 3512532 (Open Web Text)

Max Activating Token Index: 650

Text #15

Max Range: 1.8441. Min Range: -1.8441

Max Act: 1.7899. Min Act: -0.1700

Data Index: 6979749 (Open Web Text)

Max Activating Token Index: 415

Text #16

Max Range: 1.8441. Min Range: -1.8441

Max Act: 1.8025. Min Act: -0.1700

Data Index: 6887246 (Open Web Text)

Max Activating Token Index: 480

Text #17

Max Range: 1.8441. Min Range: -1.8441

Max Act: 1.7957. Min Act: -0.1700

Data Index: 2199386 (Open Web Text)

Max Activating Token Index: 993

Text #18

Max Range: 1.8441. Min Range: -1.8441

Max Act: 1.7943. Min Act: -0.1700

Data Index: 3318478 (Open Web Text)

Max Activating Token Index: 374

Text #19

Max Range: 1.8441. Min Range: -1.8441

Max Act: 1.7968. Min Act: -0.1700

Data Index: 6148131 (Open Web Text)

Max Activating Token Index: 754