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

Dataset: Open Web Text

Neuron 2846 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: 3.1518. Min Range: -3.1518

Max Act: 3.1518. Min Act: -0.1700

Data Index: 7216330 (Open Web Text)

Max Activating Token Index: 108

Text #1

Max Range: 3.1518. Min Range: -3.1518

Max Act: 3.1480. Min Act: -0.1700

Data Index: 4358618 (Open Web Text)

Max Activating Token Index: 838

Text #2

Max Range: 3.1518. Min Range: -3.1518

Max Act: 3.0890. Min Act: -0.1700

Data Index: 6006988 (Open Web Text)

Max Activating Token Index: 94

Text #3

Max Range: 3.1518. Min Range: -3.1518

Max Act: 3.0581. Min Act: -0.1700

Data Index: 1816517 (Open Web Text)

Max Activating Token Index: 638

Text #4

Max Range: 3.1518. Min Range: -3.1518

Max Act: 3.0865. Min Act: -0.1700

Data Index: 1644164 (Open Web Text)

Max Activating Token Index: 704

Text #5

Max Range: 3.1518. Min Range: -3.1518

Max Act: 3.0202. Min Act: -0.1700

Data Index: 6006987 (Open Web Text)

Max Activating Token Index: 303

Text #6

Max Range: 3.1518. Min Range: -3.1518

Max Act: 3.0128. Min Act: -0.1700

Data Index: 3229864 (Open Web Text)

Max Activating Token Index: 639

Text #7

Max Range: 3.1518. Min Range: -3.1518

Max Act: 3.0137. Min Act: -0.1700

Data Index: 1741802 (Open Web Text)

Max Activating Token Index: 493

Text #8

Max Range: 3.1518. Min Range: -3.1518

Max Act: 2.9593. Min Act: -0.1700

Data Index: 5720146 (Open Web Text)

Max Activating Token Index: 928

Text #9

Max Range: 3.1518. Min Range: -3.1518

Max Act: 3.0046. Min Act: -0.1700

Data Index: 4179846 (Open Web Text)

Max Activating Token Index: 910

Text #10

Max Range: 3.1518. Min Range: -3.1518

Max Act: 2.9877. Min Act: -0.1700

Data Index: 6604314 (Open Web Text)

Max Activating Token Index: 428

Text #11

Max Range: 3.1518. Min Range: -3.1518

Max Act: 2.9996. Min Act: -0.1700

Data Index: 3865278 (Open Web Text)

Max Activating Token Index: 560

Text #12

Max Range: 3.1518. Min Range: -3.1518

Max Act: 2.9500. Min Act: -0.1700

Data Index: 101292 (Open Web Text)

Max Activating Token Index: 385

Text #13

Max Range: 3.1518. Min Range: -3.1518

Max Act: 2.9336. Min Act: -0.1700

Data Index: 613000 (Open Web Text)

Max Activating Token Index: 929

Text #14

Max Range: 3.1518. Min Range: -3.1518

Max Act: 2.9757. Min Act: -0.1700

Data Index: 40906 (Open Web Text)

Max Activating Token Index: 506

Text #15

Max Range: 3.1518. Min Range: -3.1518

Max Act: 2.9580. Min Act: -0.1700

Data Index: 917059 (Open Web Text)

Max Activating Token Index: 383

Text #16

Max Range: 3.1518. Min Range: -3.1518

Max Act: 2.9438. Min Act: -0.1700

Data Index: 71197 (Open Web Text)

Max Activating Token Index: 841

Text #17

Max Range: 3.1518. Min Range: -3.1518

Max Act: 2.9229. Min Act: -0.1700

Data Index: 6093808 (Open Web Text)

Max Activating Token Index: 522

Text #18

Max Range: 3.1518. Min Range: -3.1518

Max Act: 2.9147. Min Act: -0.1700

Data Index: 92468 (Open Web Text)

Max Activating Token Index: 213

Text #19

Max Range: 3.1518. Min Range: -3.1518

Max Act: 2.9308. Min Act: -0.1700

Data Index: 5382365 (Open Web Text)

Max Activating Token Index: 413