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

Dataset: Open Web Text

Neuron 84 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: 1.8134. Min Range: -1.8134

Max Act: 1.8134. Min Act: -0.1700

Data Index: 8315101 (Open Web Text)

Max Activating Token Index: 539

Text #1

Max Range: 1.8134. Min Range: -1.8134

Max Act: 1.4945. Min Act: -0.1700

Data Index: 4799920 (Open Web Text)

Max Activating Token Index: 523

Text #2

Max Range: 1.8134. Min Range: -1.8134

Max Act: 1.4868. Min Act: -0.1699

Data Index: 8131645 (Open Web Text)

Max Activating Token Index: 611

Text #3

Max Range: 1.8134. Min Range: -1.8134

Max Act: 1.3703. Min Act: -0.1700

Data Index: 7455999 (Open Web Text)

Max Activating Token Index: 668

Text #4

Max Range: 1.8134. Min Range: -1.8134

Max Act: 1.3452. Min Act: -0.1700

Data Index: 5028479 (Open Web Text)

Max Activating Token Index: 503

Text #5

Max Range: 1.8134. Min Range: -1.8134

Max Act: 1.3224. Min Act: -0.1700

Data Index: 6934005 (Open Web Text)

Max Activating Token Index: 598

Text #6

Max Range: 1.8134. Min Range: -1.8134

Max Act: 1.3212. Min Act: -0.1700

Data Index: 3353495 (Open Web Text)

Max Activating Token Index: 621

Text #7

Max Range: 1.8134. Min Range: -1.8134

Max Act: 1.2698. Min Act: -0.1700

Data Index: 5200986 (Open Web Text)

Max Activating Token Index: 569

Text #8

Max Range: 1.8134. Min Range: -1.8134

Max Act: 1.2478. Min Act: -0.1700

Data Index: 6019144 (Open Web Text)

Max Activating Token Index: 628

Text #9

Max Range: 1.8134. Min Range: -1.8134

Max Act: 1.2539. Min Act: -0.1700

Data Index: 7078289 (Open Web Text)

Max Activating Token Index: 672

Text #10

Max Range: 1.8134. Min Range: -1.8134

Max Act: 1.2127. Min Act: -0.1700

Data Index: 1610857 (Open Web Text)

Max Activating Token Index: 577

Text #11

Max Range: 1.8134. Min Range: -1.8134

Max Act: 1.1684. Min Act: -0.1700

Data Index: 6575765 (Open Web Text)

Max Activating Token Index: 621

Text #12

Max Range: 1.8134. Min Range: -1.8134

Max Act: 1.1892. Min Act: -0.1700

Data Index: 3553620 (Open Web Text)

Max Activating Token Index: 664

Text #13

Max Range: 1.8134. Min Range: -1.8134

Max Act: 1.1549. Min Act: -0.1700

Data Index: 6728036 (Open Web Text)

Max Activating Token Index: 603

Text #14

Max Range: 1.8134. Min Range: -1.8134

Max Act: 1.1645. Min Act: -0.1700

Data Index: 2970039 (Open Web Text)

Max Activating Token Index: 638

Text #15

Max Range: 1.8134. Min Range: -1.8134

Max Act: 1.1454. Min Act: -0.1700

Data Index: 401356 (Open Web Text)

Max Activating Token Index: 581

Text #16

Max Range: 1.8134. Min Range: -1.8134

Max Act: 1.1573. Min Act: -0.1700

Data Index: 2418185 (Open Web Text)

Max Activating Token Index: 674

Text #17

Max Range: 1.8134. Min Range: -1.8134

Max Act: 1.1173. Min Act: -0.1700

Data Index: 4658327 (Open Web Text)

Max Activating Token Index: 496

Text #18

Max Range: 1.8134. Min Range: -1.8134

Max Act: 1.1271. Min Act: -0.1700

Data Index: 8178752 (Open Web Text)

Max Activating Token Index: 659

Text #19

Max Range: 1.8134. Min Range: -1.8134

Max Act: 1.1206. Min Act: -0.1700

Data Index: 5743591 (Open Web Text)

Max Activating Token Index: 530