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

Dataset: Open Web Text

Neuron 821 in Layer 5

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: 3.9613. Min Range: -3.9613

Max Act: 3.9613. Min Act: -0.1700

Data Index: 2237716 (Open Web Text)

Max Activating Token Index: 821

Text #1

Max Range: 3.9613. Min Range: -3.9613

Max Act: 3.9310. Min Act: -0.1700

Data Index: 1310164 (Open Web Text)

Max Activating Token Index: 593

Text #2

Max Range: 3.9613. Min Range: -3.9613

Max Act: 3.8454. Min Act: -0.1700

Data Index: 6952848 (Open Web Text)

Max Activating Token Index: 594

Text #3

Max Range: 3.9613. Min Range: -3.9613

Max Act: 3.8342. Min Act: -0.1700

Data Index: 5795925 (Open Web Text)

Max Activating Token Index: 347

Text #4

Max Range: 3.9613. Min Range: -3.9613

Max Act: 3.8567. Min Act: -0.1700

Data Index: 458493 (Open Web Text)

Max Activating Token Index: 396

Text #5

Max Range: 3.9613. Min Range: -3.9613

Max Act: 3.8444. Min Act: -0.1700

Data Index: 4345666 (Open Web Text)

Max Activating Token Index: 580

Text #6

Max Range: 3.9613. Min Range: -3.9613

Max Act: 3.8251. Min Act: -0.1700

Data Index: 2664437 (Open Web Text)

Max Activating Token Index: 995

Text #7

Max Range: 3.9613. Min Range: -3.9613

Max Act: 3.8002. Min Act: -0.1700

Data Index: 2774376 (Open Web Text)

Max Activating Token Index: 31

Text #8

Max Range: 3.9613. Min Range: -3.9613

Max Act: 3.8235. Min Act: -0.1700

Data Index: 3057202 (Open Web Text)

Max Activating Token Index: 1004

Text #9

Max Range: 3.9613. Min Range: -3.9613

Max Act: 3.8295. Min Act: -0.1700

Data Index: 289901 (Open Web Text)

Max Activating Token Index: 784

Text #10

Max Range: 3.9613. Min Range: -3.9613

Max Act: 3.7685. Min Act: -0.1700

Data Index: 2777206 (Open Web Text)

Max Activating Token Index: 450

Text #11

Max Range: 3.9613. Min Range: -3.9613

Max Act: 3.7909. Min Act: -0.1700

Data Index: 7904485 (Open Web Text)

Max Activating Token Index: 35

Text #12

Max Range: 3.9613. Min Range: -3.9613

Max Act: 3.7840. Min Act: -0.1700

Data Index: 4243242 (Open Web Text)

Max Activating Token Index: 225

Text #13

Max Range: 3.9613. Min Range: -3.9613

Max Act: 3.7895. Min Act: -0.1700

Data Index: 3892154 (Open Web Text)

Max Activating Token Index: 989

Text #14

Max Range: 3.9613. Min Range: -3.9613

Max Act: 3.7768. Min Act: -0.1700

Data Index: 900308 (Open Web Text)

Max Activating Token Index: 987

Text #15

Max Range: 3.9613. Min Range: -3.9613

Max Act: 3.7823. Min Act: -0.1700

Data Index: 8636862 (Open Web Text)

Max Activating Token Index: 987

Text #16

Max Range: 3.9613. Min Range: -3.9613

Max Act: 3.8077. Min Act: -0.1700

Data Index: 3085584 (Open Web Text)

Max Activating Token Index: 231

Text #17

Max Range: 3.9613. Min Range: -3.9613

Max Act: 3.7930. Min Act: -0.1700

Data Index: 225307 (Open Web Text)

Max Activating Token Index: 784

Text #18

Max Range: 3.9613. Min Range: -3.9613

Max Act: 3.7368. Min Act: -0.1700

Data Index: 5064799 (Open Web Text)

Max Activating Token Index: 281

Text #19

Max Range: 3.9613. Min Range: -3.9613

Max Act: 3.7425. Min Act: -0.1700

Data Index: 2073574 (Open Web Text)

Max Activating Token Index: 826