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

Dataset: Open Web Text

Neuron 2988 in Layer 6

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: 5.2625. Min Range: -5.2625

Max Act: 5.2625. Min Act: -0.1700

Data Index: 6721574 (Open Web Text)

Max Activating Token Index: 154

Text #1

Max Range: 5.2625. Min Range: -5.2625

Max Act: 5.2010. Min Act: -0.1700

Data Index: 6760639 (Open Web Text)

Max Activating Token Index: 260

Text #2

Max Range: 5.2625. Min Range: -5.2625

Max Act: 5.0748. Min Act: -0.1700

Data Index: 6912619 (Open Web Text)

Max Activating Token Index: 372

Text #3

Max Range: 5.2625. Min Range: -5.2625

Max Act: 5.0240. Min Act: -0.1700

Data Index: 6760637 (Open Web Text)

Max Activating Token Index: 893

Text #4

Max Range: 5.2625. Min Range: -5.2625

Max Act: 4.9868. Min Act: -0.1700

Data Index: 6621021 (Open Web Text)

Max Activating Token Index: 627

Text #5

Max Range: 5.2625. Min Range: -5.2625

Max Act: 5.0333. Min Act: -0.1700

Data Index: 6894390 (Open Web Text)

Max Activating Token Index: 312

Text #6

Max Range: 5.2625. Min Range: -5.2625

Max Act: 4.9715. Min Act: -0.1700

Data Index: 6574736 (Open Web Text)

Max Activating Token Index: 541

Text #7

Max Range: 5.2625. Min Range: -5.2625

Max Act: 4.9547. Min Act: -0.1700

Data Index: 2154884 (Open Web Text)

Max Activating Token Index: 172

Text #8

Max Range: 5.2625. Min Range: -5.2625

Max Act: 4.9236. Min Act: -0.1700

Data Index: 2425599 (Open Web Text)

Max Activating Token Index: 439

Text #9

Max Range: 5.2625. Min Range: -5.2625

Max Act: 4.8996. Min Act: -0.1700

Data Index: 2331724 (Open Web Text)

Max Activating Token Index: 707

Text #10

Max Range: 5.2625. Min Range: -5.2625

Max Act: 4.9084. Min Act: -0.1700

Data Index: 7884474 (Open Web Text)

Max Activating Token Index: 476

Text #11

Max Range: 5.2625. Min Range: -5.2625

Max Act: 4.9304. Min Act: -0.1700

Data Index: 7039855 (Open Web Text)

Max Activating Token Index: 22

Text #12

Max Range: 5.2625. Min Range: -5.2625

Max Act: 4.8600. Min Act: -0.1700

Data Index: 5033584 (Open Web Text)

Max Activating Token Index: 966

Text #13

Max Range: 5.2625. Min Range: -5.2625

Max Act: 4.8511. Min Act: -0.1700

Data Index: 847405 (Open Web Text)

Max Activating Token Index: 991

Text #14

Max Range: 5.2625. Min Range: -5.2625

Max Act: 4.8388. Min Act: -0.1700

Data Index: 5958367 (Open Web Text)

Max Activating Token Index: 790

Text #15

Max Range: 5.2625. Min Range: -5.2625

Max Act: 4.8567. Min Act: -0.1700

Data Index: 3915166 (Open Web Text)

Max Activating Token Index: 135

Text #16

Max Range: 5.2625. Min Range: -5.2625

Max Act: 4.8946. Min Act: -0.1700

Data Index: 4332198 (Open Web Text)

Max Activating Token Index: 444

Text #17

Max Range: 5.2625. Min Range: -5.2625

Max Act: 4.8160. Min Act: -0.1700

Data Index: 3183208 (Open Web Text)

Max Activating Token Index: 351

Text #18

Max Range: 5.2625. Min Range: -5.2625

Max Act: 4.8456. Min Act: -0.1700

Data Index: 3203858 (Open Web Text)

Max Activating Token Index: 431

Text #19

Max Range: 5.2625. Min Range: -5.2625

Max Act: 4.8635. Min Act: -0.1700

Data Index: 1881835 (Open Web Text)

Max Activating Token Index: 457