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

Dataset: Open Web Text

Neuron 965 in Layer 1

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: 2.0702. Min Range: -2.0702

Max Act: 2.0702. Min Act: -0.1700

Data Index: 1227892 (Open Web Text)

Max Activating Token Index: 319

Text #1

Max Range: 2.0702. Min Range: -2.0702

Max Act: 2.0480. Min Act: -0.1700

Data Index: 355013 (Open Web Text)

Max Activating Token Index: 656

Text #2

Max Range: 2.0702. Min Range: -2.0702

Max Act: 2.0123. Min Act: -0.1700

Data Index: 1663285 (Open Web Text)

Max Activating Token Index: 704

Text #3

Max Range: 2.0702. Min Range: -2.0702

Max Act: 1.9948. Min Act: -0.1700

Data Index: 3331501 (Open Web Text)

Max Activating Token Index: 350

Text #4

Max Range: 2.0702. Min Range: -2.0702

Max Act: 1.9715. Min Act: -0.1700

Data Index: 59302 (Open Web Text)

Max Activating Token Index: 46

Text #5

Max Range: 2.0702. Min Range: -2.0702

Max Act: 1.9356. Min Act: -0.1700

Data Index: 4467834 (Open Web Text)

Max Activating Token Index: 701

Text #6

Max Range: 2.0702. Min Range: -2.0702

Max Act: 1.9484. Min Act: -0.1700

Data Index: 4467835 (Open Web Text)

Max Activating Token Index: 765

Text #7

Max Range: 2.0702. Min Range: -2.0702

Max Act: 1.9414. Min Act: -0.1700

Data Index: 4590260 (Open Web Text)

Max Activating Token Index: 383

Text #8

Max Range: 2.0702. Min Range: -2.0702

Max Act: 1.9319. Min Act: -0.1700

Data Index: 4499783 (Open Web Text)

Max Activating Token Index: 465

Text #9

Max Range: 2.0702. Min Range: -2.0702

Max Act: 1.9143. Min Act: -0.1700

Data Index: 2005283 (Open Web Text)

Max Activating Token Index: 564

Text #10

Max Range: 2.0702. Min Range: -2.0702

Max Act: 1.9261. Min Act: -0.1700

Data Index: 5372308 (Open Web Text)

Max Activating Token Index: 983

Text #11

Max Range: 2.0702. Min Range: -2.0702

Max Act: 1.9236. Min Act: -0.1700

Data Index: 5046098 (Open Web Text)

Max Activating Token Index: 49

Text #12

Max Range: 2.0702. Min Range: -2.0702

Max Act: 1.9268. Min Act: -0.1700

Data Index: 1320060 (Open Web Text)

Max Activating Token Index: 751

Text #13

Max Range: 2.0702. Min Range: -2.0702

Max Act: 1.9209. Min Act: -0.1700

Data Index: 1250489 (Open Web Text)

Max Activating Token Index: 346

Text #14

Max Range: 2.0702. Min Range: -2.0702

Max Act: 1.9272. Min Act: -0.1700

Data Index: 405934 (Open Web Text)

Max Activating Token Index: 205

Text #15

Max Range: 2.0702. Min Range: -2.0702

Max Act: 1.8969. Min Act: -0.1700

Data Index: 3523014 (Open Web Text)

Max Activating Token Index: 524

Text #16

Max Range: 2.0702. Min Range: -2.0702

Max Act: 1.8999. Min Act: -0.1700

Data Index: 3552835 (Open Web Text)

Max Activating Token Index: 352

Text #17

Max Range: 2.0702. Min Range: -2.0702

Max Act: 1.9061. Min Act: -0.1700

Data Index: 3963009 (Open Web Text)

Max Activating Token Index: 589

Text #18

Max Range: 2.0702. Min Range: -2.0702

Max Act: 1.9098. Min Act: -0.1700

Data Index: 1771120 (Open Web Text)

Max Activating Token Index: 136

Text #19

Max Range: 2.0702. Min Range: -2.0702

Max Act: 1.9020. Min Act: -0.1700

Data Index: 1939522 (Open Web Text)

Max Activating Token Index: 725