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

Dataset: Open Web Text

Neuron 1538 in Layer 5

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: 4.1156. Min Range: -4.1156

Max Act: 4.0998. Min Act: -0.1700

Data Index: 5412162 (Open Web Text)

Max Activating Token Index: 458

Text #1

Max Range: 4.1156. Min Range: -4.1156

Max Act: 4.1156. Min Act: -0.1700

Data Index: 4287897 (Open Web Text)

Max Activating Token Index: 891

Text #2

Max Range: 4.1156. Min Range: -4.1156

Max Act: 4.1137. Min Act: -0.1700

Data Index: 7121353 (Open Web Text)

Max Activating Token Index: 98

Text #3

Max Range: 4.1156. Min Range: -4.1156

Max Act: 4.0522. Min Act: -0.1700

Data Index: 526424 (Open Web Text)

Max Activating Token Index: 891

Text #4

Max Range: 4.1156. Min Range: -4.1156

Max Act: 4.0585. Min Act: -0.1700

Data Index: 4429128 (Open Web Text)

Max Activating Token Index: 718

Text #5

Max Range: 4.1156. Min Range: -4.1156

Max Act: 4.0470. Min Act: -0.1700

Data Index: 6670841 (Open Web Text)

Max Activating Token Index: 493

Text #6

Max Range: 4.1156. Min Range: -4.1156

Max Act: 4.1011. Min Act: -0.1700

Data Index: 4706065 (Open Web Text)

Max Activating Token Index: 451

Text #7

Max Range: 4.1156. Min Range: -4.1156

Max Act: 4.0734. Min Act: -0.1700

Data Index: 2590634 (Open Web Text)

Max Activating Token Index: 322

Text #8

Max Range: 4.1156. Min Range: -4.1156

Max Act: 4.0132. Min Act: -0.1700

Data Index: 2803624 (Open Web Text)

Max Activating Token Index: 913

Text #9

Max Range: 4.1156. Min Range: -4.1156

Max Act: 4.0326. Min Act: -0.1700

Data Index: 3715332 (Open Web Text)

Max Activating Token Index: 171

Text #10

Max Range: 4.1156. Min Range: -4.1156

Max Act: 4.0467. Min Act: -0.1700

Data Index: 7581179 (Open Web Text)

Max Activating Token Index: 63

Text #11

Max Range: 4.1156. Min Range: -4.1156

Max Act: 4.0357. Min Act: -0.1700

Data Index: 6199621 (Open Web Text)

Max Activating Token Index: 706

Text #12

Max Range: 4.1156. Min Range: -4.1156

Max Act: 3.9722. Min Act: -0.1700

Data Index: 5765736 (Open Web Text)

Max Activating Token Index: 463

Text #13

Max Range: 4.1156. Min Range: -4.1156

Max Act: 3.9911. Min Act: -0.1700

Data Index: 6222434 (Open Web Text)

Max Activating Token Index: 873

Text #14

Max Range: 4.1156. Min Range: -4.1156

Max Act: 4.0149. Min Act: -0.1700

Data Index: 8566326 (Open Web Text)

Max Activating Token Index: 190

Text #15

Max Range: 4.1156. Min Range: -4.1156

Max Act: 4.0007. Min Act: -0.1700

Data Index: 7581181 (Open Web Text)

Max Activating Token Index: 238

Text #16

Max Range: 4.1156. Min Range: -4.1156

Max Act: 3.9728. Min Act: -0.1700

Data Index: 1650715 (Open Web Text)

Max Activating Token Index: 213

Text #17

Max Range: 4.1156. Min Range: -4.1156

Max Act: 4.0185. Min Act: -0.1700

Data Index: 5567421 (Open Web Text)

Max Activating Token Index: 627

Text #18

Max Range: 4.1156. Min Range: -4.1156

Max Act: 3.9703. Min Act: -0.1700

Data Index: 5192633 (Open Web Text)

Max Activating Token Index: 828

Text #19

Max Range: 4.1156. Min Range: -4.1156

Max Act: 3.9671. Min Act: -0.1700

Data Index: 6413805 (Open Web Text)

Max Activating Token Index: 948