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

Dataset: Open Web Text

Neuron 226 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: 4.9965. Min Range: -4.9965

Max Act: 4.9965. Min Act: -0.1700

Data Index: 3935876 (Open Web Text)

Max Activating Token Index: 257

Text #1

Max Range: 4.9965. Min Range: -4.9965

Max Act: 4.9356. Min Act: -0.1700

Data Index: 2562627 (Open Web Text)

Max Activating Token Index: 541

Text #2

Max Range: 4.9965. Min Range: -4.9965

Max Act: 4.9303. Min Act: -0.1700

Data Index: 2968950 (Open Web Text)

Max Activating Token Index: 792

Text #3

Max Range: 4.9965. Min Range: -4.9965

Max Act: 4.9245. Min Act: -0.1700

Data Index: 184091 (Open Web Text)

Max Activating Token Index: 904

Text #4

Max Range: 4.9965. Min Range: -4.9965

Max Act: 4.9260. Min Act: -0.1700

Data Index: 988838 (Open Web Text)

Max Activating Token Index: 891

Text #5

Max Range: 4.9965. Min Range: -4.9965

Max Act: 4.9381. Min Act: -0.1700

Data Index: 3513971 (Open Web Text)

Max Activating Token Index: 728

Text #6

Max Range: 4.9965. Min Range: -4.9965

Max Act: 4.9041. Min Act: -0.1700

Data Index: 7775795 (Open Web Text)

Max Activating Token Index: 273

Text #7

Max Range: 4.9965. Min Range: -4.9965

Max Act: 4.8981. Min Act: -0.1700

Data Index: 3613504 (Open Web Text)

Max Activating Token Index: 607

Text #8

Max Range: 4.9965. Min Range: -4.9965

Max Act: 4.8845. Min Act: -0.1700

Data Index: 7805501 (Open Web Text)

Max Activating Token Index: 435

Text #9

Max Range: 4.9965. Min Range: -4.9965

Max Act: 4.8763. Min Act: -0.1700

Data Index: 6171175 (Open Web Text)

Max Activating Token Index: 675

Text #10

Max Range: 4.9965. Min Range: -4.9965

Max Act: 4.8592. Min Act: -0.1700

Data Index: 2316434 (Open Web Text)

Max Activating Token Index: 592

Text #11

Max Range: 4.9965. Min Range: -4.9965

Max Act: 4.8698. Min Act: -0.1700

Data Index: 1927636 (Open Web Text)

Max Activating Token Index: 412

Text #12

Max Range: 4.9965. Min Range: -4.9965

Max Act: 4.8502. Min Act: -0.1700

Data Index: 7911415 (Open Web Text)

Max Activating Token Index: 98

Text #13

Max Range: 4.9965. Min Range: -4.9965

Max Act: 4.8834. Min Act: -0.1700

Data Index: 4608625 (Open Web Text)

Max Activating Token Index: 294

Text #14

Max Range: 4.9965. Min Range: -4.9965

Max Act: 4.8824. Min Act: -0.1700

Data Index: 4157730 (Open Web Text)

Max Activating Token Index: 338

Text #15

Max Range: 4.9965. Min Range: -4.9965

Max Act: 4.8221. Min Act: -0.1700

Data Index: 2065521 (Open Web Text)

Max Activating Token Index: 399

Text #16

Max Range: 4.9965. Min Range: -4.9965

Max Act: 4.8408. Min Act: -0.1700

Data Index: 3717625 (Open Web Text)

Max Activating Token Index: 671

Text #17

Max Range: 4.9965. Min Range: -4.9965

Max Act: 4.8517. Min Act: -0.1700

Data Index: 1910636 (Open Web Text)

Max Activating Token Index: 744

Text #18

Max Range: 4.9965. Min Range: -4.9965

Max Act: 4.8494. Min Act: -0.1700

Data Index: 61658 (Open Web Text)

Max Activating Token Index: 90

Text #19

Max Range: 4.9965. Min Range: -4.9965

Max Act: 4.8215. Min Act: -0.1700

Data Index: 3873535 (Open Web Text)

Max Activating Token Index: 861