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

Dataset: Open Web Text

Neuron 400 in Layer 0

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: 4.4351. Min Range: -4.4351

Max Act: 4.4351. Min Act: -0.1700

Data Index: 6261287 (Open Web Text)

Max Activating Token Index: 4

Text #1

Max Range: 4.4351. Min Range: -4.4351

Max Act: 4.2763. Min Act: -0.1700

Data Index: 7848139 (Open Web Text)

Max Activating Token Index: 9

Text #2

Max Range: 4.4351. Min Range: -4.4351

Max Act: 4.2271. Min Act: -0.1700

Data Index: 1459042 (Open Web Text)

Max Activating Token Index: 9

Text #3

Max Range: 4.4351. Min Range: -4.4351

Max Act: 4.2090. Min Act: -0.1700

Data Index: 3078312 (Open Web Text)

Max Activating Token Index: 16

Text #4

Max Range: 4.4351. Min Range: -4.4351

Max Act: 4.1687. Min Act: -0.1700

Data Index: 6255145 (Open Web Text)

Max Activating Token Index: 37

Text #5

Max Range: 4.4351. Min Range: -4.4351

Max Act: 4.1961. Min Act: -0.1700

Data Index: 7848141 (Open Web Text)

Max Activating Token Index: 11

Text #6

Max Range: 4.4351. Min Range: -4.4351

Max Act: 4.1728. Min Act: -0.1700

Data Index: 7797149 (Open Web Text)

Max Activating Token Index: 15

Text #7

Max Range: 4.4351. Min Range: -4.4351

Max Act: 4.1676. Min Act: -0.1700

Data Index: 7658458 (Open Web Text)

Max Activating Token Index: 3

Text #8

Max Range: 4.4351. Min Range: -4.4351

Max Act: 4.1502. Min Act: -0.1700

Data Index: 7848140 (Open Web Text)

Max Activating Token Index: 23

Text #9

Max Range: 4.4351. Min Range: -4.4351

Max Act: 4.1062. Min Act: -0.1700

Data Index: 753207 (Open Web Text)

Max Activating Token Index: 5

Text #10

Max Range: 4.4351. Min Range: -4.4351

Max Act: 4.1277. Min Act: -0.1700

Data Index: 129032 (Open Web Text)

Max Activating Token Index: 31

Text #11

Max Range: 4.4351. Min Range: -4.4351

Max Act: 4.1104. Min Act: -0.1700

Data Index: 1978821 (Open Web Text)

Max Activating Token Index: 12

Text #12

Max Range: 4.4351. Min Range: -4.4351

Max Act: 4.1128. Min Act: -0.1700

Data Index: 2308848 (Open Web Text)

Max Activating Token Index: 18

Text #13

Max Range: 4.4351. Min Range: -4.4351

Max Act: 4.1247. Min Act: -0.1700

Data Index: 7339392 (Open Web Text)

Max Activating Token Index: 12

Text #14

Max Range: 4.4351. Min Range: -4.4351

Max Act: 4.1287. Min Act: -0.1700

Data Index: 8031579 (Open Web Text)

Max Activating Token Index: 68

Text #15

Max Range: 4.4351. Min Range: -4.4351

Max Act: 4.0798. Min Act: -0.1700

Data Index: 7455917 (Open Web Text)

Max Activating Token Index: 22

Text #16

Max Range: 4.4351. Min Range: -4.4351

Max Act: 4.0884. Min Act: -0.1700

Data Index: 1953104 (Open Web Text)

Max Activating Token Index: 52

Text #17

Max Range: 4.4351. Min Range: -4.4351

Max Act: 4.0935. Min Act: -0.1700

Data Index: 4688662 (Open Web Text)

Max Activating Token Index: 68

Text #18

Max Range: 4.4351. Min Range: -4.4351

Max Act: 4.0725. Min Act: -0.1700

Data Index: 5307162 (Open Web Text)

Max Activating Token Index: 29

Text #19

Max Range: 4.4351. Min Range: -4.4351

Max Act: 4.0458. Min Act: -0.1696

Data Index: 3675350 (Open Web Text)

Max Activating Token Index: 52