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

Dataset: Open Web Text

Neuron 1508 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: 4.1315. Min Range: -4.1315

Max Act: 4.1315. Min Act: -0.1700

Data Index: 1860649 (Open Web Text)

Max Activating Token Index: 928

Text #1

Max Range: 4.1315. Min Range: -4.1315

Max Act: 4.0649. Min Act: -0.1700

Data Index: 297108 (Open Web Text)

Max Activating Token Index: 354

Text #2

Max Range: 4.1315. Min Range: -4.1315

Max Act: 4.0658. Min Act: -0.1700

Data Index: 2203462 (Open Web Text)

Max Activating Token Index: 6

Text #3

Max Range: 4.1315. Min Range: -4.1315

Max Act: 4.0244. Min Act: -0.1700

Data Index: 380600 (Open Web Text)

Max Activating Token Index: 990

Text #4

Max Range: 4.1315. Min Range: -4.1315

Max Act: 4.0458. Min Act: -0.1700

Data Index: 1566480 (Open Web Text)

Max Activating Token Index: 10

Text #5

Max Range: 4.1315. Min Range: -4.1315

Max Act: 4.0174. Min Act: -0.1700

Data Index: 2695211 (Open Web Text)

Max Activating Token Index: 806

Text #6

Max Range: 4.1315. Min Range: -4.1315

Max Act: 3.9916. Min Act: -0.1700

Data Index: 2121972 (Open Web Text)

Max Activating Token Index: 948

Text #7

Max Range: 4.1315. Min Range: -4.1315

Max Act: 4.0087. Min Act: -0.1700

Data Index: 4544766 (Open Web Text)

Max Activating Token Index: 354

Text #8

Max Range: 4.1315. Min Range: -4.1315

Max Act: 4.0076. Min Act: -0.1700

Data Index: 2348958 (Open Web Text)

Max Activating Token Index: 403

Text #9

Max Range: 4.1315. Min Range: -4.1315

Max Act: 3.9727. Min Act: -0.1700

Data Index: 6678414 (Open Web Text)

Max Activating Token Index: 731

Text #10

Max Range: 4.1315. Min Range: -4.1315

Max Act: 3.9882. Min Act: -0.1700

Data Index: 852523 (Open Web Text)

Max Activating Token Index: 363

Text #11

Max Range: 4.1315. Min Range: -4.1315

Max Act: 3.9641. Min Act: -0.1700

Data Index: 1268718 (Open Web Text)

Max Activating Token Index: 80

Text #12

Max Range: 4.1315. Min Range: -4.1315

Max Act: 3.9571. Min Act: -0.1700

Data Index: 7294335 (Open Web Text)

Max Activating Token Index: 382

Text #13

Max Range: 4.1315. Min Range: -4.1315

Max Act: 3.9674. Min Act: -0.1700

Data Index: 2398568 (Open Web Text)

Max Activating Token Index: 814

Text #14

Max Range: 4.1315. Min Range: -4.1315

Max Act: 3.9507. Min Act: -0.1700

Data Index: 6934878 (Open Web Text)

Max Activating Token Index: 996

Text #15

Max Range: 4.1315. Min Range: -4.1315

Max Act: 3.9632. Min Act: -0.1700

Data Index: 5771181 (Open Web Text)

Max Activating Token Index: 955

Text #16

Max Range: 4.1315. Min Range: -4.1315

Max Act: 3.9781. Min Act: -0.1700

Data Index: 3525288 (Open Web Text)

Max Activating Token Index: 721

Text #17

Max Range: 4.1315. Min Range: -4.1315

Max Act: 3.9768. Min Act: -0.1700

Data Index: 2006245 (Open Web Text)

Max Activating Token Index: 100

Text #18

Max Range: 4.1315. Min Range: -4.1315

Max Act: 3.9653. Min Act: -0.1700

Data Index: 3132949 (Open Web Text)

Max Activating Token Index: 76

Text #19

Max Range: 4.1315. Min Range: -4.1315

Max Act: 3.9563. Min Act: -0.1700

Data Index: 6658743 (Open Web Text)

Max Activating Token Index: 309