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

Dataset: Open Web Text

Neuron 494 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: 3.3294. Min Range: -3.3294

Max Act: 3.3294. Min Act: -0.1700

Data Index: 6669290 (Open Web Text)

Max Activating Token Index: 2

Text #1

Max Range: 3.3294. Min Range: -3.3294

Max Act: 3.2284. Min Act: -0.1700

Data Index: 62852 (Open Web Text)

Max Activating Token Index: 357

Text #2

Max Range: 3.3294. Min Range: -3.3294

Max Act: 3.2385. Min Act: -0.1700

Data Index: 1598824 (Open Web Text)

Max Activating Token Index: 57

Text #3

Max Range: 3.3294. Min Range: -3.3294

Max Act: 3.2943. Min Act: -0.1700

Data Index: 8626300 (Open Web Text)

Max Activating Token Index: 894

Text #4

Max Range: 3.3294. Min Range: -3.3294

Max Act: 3.2418. Min Act: -0.1700

Data Index: 6643323 (Open Web Text)

Max Activating Token Index: 657

Text #5

Max Range: 3.3294. Min Range: -3.3294

Max Act: 3.2297. Min Act: -0.1700

Data Index: 3674568 (Open Web Text)

Max Activating Token Index: 195

Text #6

Max Range: 3.3294. Min Range: -3.3294

Max Act: 3.2084. Min Act: -0.1700

Data Index: 6235330 (Open Web Text)

Max Activating Token Index: 711

Text #7

Max Range: 3.3294. Min Range: -3.3294

Max Act: 3.1965. Min Act: -0.1700

Data Index: 5123222 (Open Web Text)

Max Activating Token Index: 373

Text #8

Max Range: 3.3294. Min Range: -3.3294

Max Act: 3.2037. Min Act: -0.1700

Data Index: 2660467 (Open Web Text)

Max Activating Token Index: 718

Text #9

Max Range: 3.3294. Min Range: -3.3294

Max Act: 3.1642. Min Act: -0.1700

Data Index: 2185049 (Open Web Text)

Max Activating Token Index: 542

Text #10

Max Range: 3.3294. Min Range: -3.3294

Max Act: 3.1597. Min Act: -0.1700

Data Index: 5651655 (Open Web Text)

Max Activating Token Index: 2

Text #11

Max Range: 3.3294. Min Range: -3.3294

Max Act: 3.1774. Min Act: -0.1700

Data Index: 8114812 (Open Web Text)

Max Activating Token Index: 149

Text #12

Max Range: 3.3294. Min Range: -3.3294

Max Act: 3.0813. Min Act: -0.1700

Data Index: 7367607 (Open Web Text)

Max Activating Token Index: 801

Text #13

Max Range: 3.3294. Min Range: -3.3294

Max Act: 3.1316. Min Act: -0.1700

Data Index: 3600240 (Open Web Text)

Max Activating Token Index: 26

Text #14

Max Range: 3.3294. Min Range: -3.3294

Max Act: 3.1238. Min Act: -0.1700

Data Index: 6787360 (Open Web Text)

Max Activating Token Index: 5

Text #15

Max Range: 3.3294. Min Range: -3.3294

Max Act: 3.1447. Min Act: -0.1700

Data Index: 4073224 (Open Web Text)

Max Activating Token Index: 5

Text #16

Max Range: 3.3294. Min Range: -3.3294

Max Act: 3.1452. Min Act: -0.1700

Data Index: 5480994 (Open Web Text)

Max Activating Token Index: 666

Text #17

Max Range: 3.3294. Min Range: -3.3294

Max Act: 3.0798. Min Act: -0.1700

Data Index: 4263646 (Open Web Text)

Max Activating Token Index: 770

Text #18

Max Range: 3.3294. Min Range: -3.3294

Max Act: 3.0850. Min Act: -0.1700

Data Index: 1496306 (Open Web Text)

Max Activating Token Index: 621

Text #19

Max Range: 3.3294. Min Range: -3.3294

Max Act: 3.0684. Min Act: -0.1700

Data Index: 4024856 (Open Web Text)

Max Activating Token Index: 623