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

Dataset: Open Web Text

Neuron 455 in Layer 4

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: 1.7316. Min Range: -1.7316

Max Act: 1.7274. Min Act: -0.1700

Data Index: 6806327 (Open Web Text)

Max Activating Token Index: 347

Text #1

Max Range: 1.7316. Min Range: -1.7316

Max Act: 1.7316. Min Act: -0.1700

Data Index: 7207832 (Open Web Text)

Max Activating Token Index: 109

Text #2

Max Range: 1.7316. Min Range: -1.7316

Max Act: 1.7169. Min Act: -0.1700

Data Index: 2187812 (Open Web Text)

Max Activating Token Index: 337

Text #3

Max Range: 1.7316. Min Range: -1.7316

Max Act: 1.7002. Min Act: -0.1700

Data Index: 6621418 (Open Web Text)

Max Activating Token Index: 913

Text #4

Max Range: 1.7316. Min Range: -1.7316

Max Act: 1.7193. Min Act: -0.1700

Data Index: 7398753 (Open Web Text)

Max Activating Token Index: 372

Text #5

Max Range: 1.7316. Min Range: -1.7316

Max Act: 1.7045. Min Act: -0.1700

Data Index: 3629554 (Open Web Text)

Max Activating Token Index: 43

Text #6

Max Range: 1.7316. Min Range: -1.7316

Max Act: 1.6979. Min Act: -0.1700

Data Index: 6621405 (Open Web Text)

Max Activating Token Index: 833

Text #7

Max Range: 1.7316. Min Range: -1.7316

Max Act: 1.6862. Min Act: -0.1700

Data Index: 6621411 (Open Web Text)

Max Activating Token Index: 878

Text #8

Max Range: 1.7316. Min Range: -1.7316

Max Act: 1.6963. Min Act: -0.1700

Data Index: 6621421 (Open Web Text)

Max Activating Token Index: 952

Text #9

Max Range: 1.7316. Min Range: -1.7316

Max Act: 1.6889. Min Act: -0.1700

Data Index: 8289445 (Open Web Text)

Max Activating Token Index: 3

Text #10

Max Range: 1.7316. Min Range: -1.7316

Max Act: 1.6815. Min Act: -0.1700

Data Index: 8105547 (Open Web Text)

Max Activating Token Index: 585

Text #11

Max Range: 1.7316. Min Range: -1.7316

Max Act: 1.6760. Min Act: -0.1700

Data Index: 3228521 (Open Web Text)

Max Activating Token Index: 38

Text #12

Max Range: 1.7316. Min Range: -1.7316

Max Act: 1.6742. Min Act: -0.1700

Data Index: 44266 (Open Web Text)

Max Activating Token Index: 944

Text #13

Max Range: 1.7316. Min Range: -1.7316

Max Act: 1.6634. Min Act: -0.1700

Data Index: 4892191 (Open Web Text)

Max Activating Token Index: 900

Text #14

Max Range: 1.7316. Min Range: -1.7316

Max Act: 1.6628. Min Act: -0.1700

Data Index: 44271 (Open Web Text)

Max Activating Token Index: 897

Text #15

Max Range: 1.7316. Min Range: -1.7316

Max Act: 1.6622. Min Act: -0.1700

Data Index: 7398760 (Open Web Text)

Max Activating Token Index: 445

Text #16

Max Range: 1.7316. Min Range: -1.7316

Max Act: 1.6705. Min Act: -0.1700

Data Index: 7398776 (Open Web Text)

Max Activating Token Index: 863

Text #17

Max Range: 1.7316. Min Range: -1.7316

Max Act: 1.6661. Min Act: -0.1700

Data Index: 7649279 (Open Web Text)

Max Activating Token Index: 118

Text #18

Max Range: 1.7316. Min Range: -1.7316

Max Act: 1.6601. Min Act: -0.1700

Data Index: 6621412 (Open Web Text)

Max Activating Token Index: 981

Text #19

Max Range: 1.7316. Min Range: -1.7316

Max Act: 1.6603. Min Act: -0.1700

Data Index: 6621402 (Open Web Text)

Max Activating Token Index: 437