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

Dataset: Open Web Text

Neuron 1481 in Layer 0

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: 3.9025. Min Range: -3.9025

Max Act: 3.9025. Min Act: -0.1700

Data Index: 5212020 (Open Web Text)

Max Activating Token Index: 235

Text #1

Max Range: 3.9025. Min Range: -3.9025

Max Act: 3.8725. Min Act: -0.1700

Data Index: 536673 (Open Web Text)

Max Activating Token Index: 6

Text #2

Max Range: 3.9025. Min Range: -3.9025

Max Act: 3.8563. Min Act: -0.1700

Data Index: 5212019 (Open Web Text)

Max Activating Token Index: 832

Text #3

Max Range: 3.9025. Min Range: -3.9025

Max Act: 3.7837. Min Act: -0.1700

Data Index: 5275031 (Open Web Text)

Max Activating Token Index: 22

Text #4

Max Range: 3.9025. Min Range: -3.9025

Max Act: 3.7707. Min Act: -0.1700

Data Index: 2898305 (Open Web Text)

Max Activating Token Index: 4

Text #5

Max Range: 3.9025. Min Range: -3.9025

Max Act: 3.7737. Min Act: -0.1700

Data Index: 673009 (Open Web Text)

Max Activating Token Index: 4

Text #6

Max Range: 3.9025. Min Range: -3.9025

Max Act: 3.7506. Min Act: -0.1700

Data Index: 6343427 (Open Web Text)

Max Activating Token Index: 5

Text #7

Max Range: 3.9025. Min Range: -3.9025

Max Act: 3.7375. Min Act: -0.1700

Data Index: 6949485 (Open Web Text)

Max Activating Token Index: 4

Text #8

Max Range: 3.9025. Min Range: -3.9025

Max Act: 3.7030. Min Act: -0.1700

Data Index: 5535992 (Open Web Text)

Max Activating Token Index: 9

Text #9

Max Range: 3.9025. Min Range: -3.9025

Max Act: 3.7284. Min Act: -0.1700

Data Index: 4097624 (Open Web Text)

Max Activating Token Index: 4

Text #10

Max Range: 3.9025. Min Range: -3.9025

Max Act: 3.6788. Min Act: -0.1700

Data Index: 4862698 (Open Web Text)

Max Activating Token Index: 5

Text #11

Max Range: 3.9025. Min Range: -3.9025

Max Act: 3.6982. Min Act: -0.1700

Data Index: 5192160 (Open Web Text)

Max Activating Token Index: 5

Text #12

Max Range: 3.9025. Min Range: -3.9025

Max Act: 3.6953. Min Act: -0.1700

Data Index: 4603314 (Open Web Text)

Max Activating Token Index: 4

Text #13

Max Range: 3.9025. Min Range: -3.9025

Max Act: 3.6945. Min Act: -0.1700

Data Index: 314889 (Open Web Text)

Max Activating Token Index: 44

Text #14

Max Range: 3.9025. Min Range: -3.9025

Max Act: 3.6696. Min Act: -0.1700

Data Index: 4558982 (Open Web Text)

Max Activating Token Index: 3

Text #15

Max Range: 3.9025. Min Range: -3.9025

Max Act: 3.6960. Min Act: -0.1700

Data Index: 8286024 (Open Web Text)

Max Activating Token Index: 4

Text #16

Max Range: 3.9025. Min Range: -3.9025

Max Act: 3.6811. Min Act: -0.1700

Data Index: 6382449 (Open Web Text)

Max Activating Token Index: 8

Text #17

Max Range: 3.9025. Min Range: -3.9025

Max Act: 3.6423. Min Act: -0.1700

Data Index: 523947 (Open Web Text)

Max Activating Token Index: 3

Text #18

Max Range: 3.9025. Min Range: -3.9025

Max Act: 3.6467. Min Act: -0.1700

Data Index: 2868290 (Open Web Text)

Max Activating Token Index: 4

Text #19

Max Range: 3.9025. Min Range: -3.9025

Max Act: 3.6423. Min Act: -0.1700

Data Index: 4702653 (Open Web Text)

Max Activating Token Index: 3