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

Dataset: Open Web Text

Neuron 643 in Layer 2

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: 4.1773. Min Range: -4.1773

Max Act: 4.1773. Min Act: -0.1700

Data Index: 5476159 (Open Web Text)

Max Activating Token Index: 324

Text #1

Max Range: 4.1773. Min Range: -4.1773

Max Act: 4.1152. Min Act: -0.1700

Data Index: 8542216 (Open Web Text)

Max Activating Token Index: 547

Text #2

Max Range: 4.1773. Min Range: -4.1773

Max Act: 4.1302. Min Act: -0.1700

Data Index: 2499085 (Open Web Text)

Max Activating Token Index: 435

Text #3

Max Range: 4.1773. Min Range: -4.1773

Max Act: 4.0831. Min Act: -0.1700

Data Index: 3975718 (Open Web Text)

Max Activating Token Index: 155

Text #4

Max Range: 4.1773. Min Range: -4.1773

Max Act: 4.0755. Min Act: -0.1700

Data Index: 4570756 (Open Web Text)

Max Activating Token Index: 18

Text #5

Max Range: 4.1773. Min Range: -4.1773

Max Act: 4.1086. Min Act: -0.1700

Data Index: 5208364 (Open Web Text)

Max Activating Token Index: 312

Text #6

Max Range: 4.1773. Min Range: -4.1773

Max Act: 4.0933. Min Act: -0.1700

Data Index: 4160322 (Open Web Text)

Max Activating Token Index: 698

Text #7

Max Range: 4.1773. Min Range: -4.1773

Max Act: 4.0528. Min Act: -0.1700

Data Index: 2974972 (Open Web Text)

Max Activating Token Index: 574

Text #8

Max Range: 4.1773. Min Range: -4.1773

Max Act: 4.0680. Min Act: -0.1700

Data Index: 1600067 (Open Web Text)

Max Activating Token Index: 26

Text #9

Max Range: 4.1773. Min Range: -4.1773

Max Act: 4.0318. Min Act: -0.1700

Data Index: 8188040 (Open Web Text)

Max Activating Token Index: 303

Text #10

Max Range: 4.1773. Min Range: -4.1773

Max Act: 4.0448. Min Act: -0.1700

Data Index: 3088060 (Open Web Text)

Max Activating Token Index: 1022

Text #11

Max Range: 4.1773. Min Range: -4.1773

Max Act: 4.0510. Min Act: -0.1700

Data Index: 1241843 (Open Web Text)

Max Activating Token Index: 992

Text #12

Max Range: 4.1773. Min Range: -4.1773

Max Act: 4.0354. Min Act: -0.1700

Data Index: 4627854 (Open Web Text)

Max Activating Token Index: 22

Text #13

Max Range: 4.1773. Min Range: -4.1773

Max Act: 4.0298. Min Act: -0.1700

Data Index: 3416441 (Open Web Text)

Max Activating Token Index: 460

Text #14

Max Range: 4.1773. Min Range: -4.1773

Max Act: 4.0409. Min Act: -0.1700

Data Index: 3270458 (Open Web Text)

Max Activating Token Index: 33

Text #15

Max Range: 4.1773. Min Range: -4.1773

Max Act: 4.0083. Min Act: -0.1700

Data Index: 4409601 (Open Web Text)

Max Activating Token Index: 403

Text #16

Max Range: 4.1773. Min Range: -4.1773

Max Act: 4.0316. Min Act: -0.1700

Data Index: 4409599 (Open Web Text)

Max Activating Token Index: 892

Text #17

Max Range: 4.1773. Min Range: -4.1773

Max Act: 4.0253. Min Act: -0.1700

Data Index: 1357257 (Open Web Text)

Max Activating Token Index: 47

Text #18

Max Range: 4.1773. Min Range: -4.1773

Max Act: 4.0296. Min Act: -0.1700

Data Index: 5048150 (Open Web Text)

Max Activating Token Index: 263

Text #19

Max Range: 4.1773. Min Range: -4.1773

Max Act: 4.0066. Min Act: -0.1700

Data Index: 5047412 (Open Web Text)

Max Activating Token Index: 260