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

Dataset: Open Web Text

Neuron 63 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: 3.3417. Min Range: -3.3417

Max Act: 3.3415. Min Act: -0.1700

Data Index: 463232 (Open Web Text)

Max Activating Token Index: 914

Text #1

Max Range: 3.3417. Min Range: -3.3417

Max Act: 3.3417. Min Act: -0.1700

Data Index: 3739395 (Open Web Text)

Max Activating Token Index: 637

Text #2

Max Range: 3.3417. Min Range: -3.3417

Max Act: 3.2529. Min Act: -0.1700

Data Index: 9147 (Open Web Text)

Max Activating Token Index: 981

Text #3

Max Range: 3.3417. Min Range: -3.3417

Max Act: 3.2197. Min Act: -0.1700

Data Index: 4266098 (Open Web Text)

Max Activating Token Index: 572

Text #4

Max Range: 3.3417. Min Range: -3.3417

Max Act: 3.2391. Min Act: -0.1700

Data Index: 2039735 (Open Web Text)

Max Activating Token Index: 692

Text #5

Max Range: 3.3417. Min Range: -3.3417

Max Act: 3.2025. Min Act: -0.1700

Data Index: 6698948 (Open Web Text)

Max Activating Token Index: 304

Text #6

Max Range: 3.3417. Min Range: -3.3417

Max Act: 3.2231. Min Act: -0.1700

Data Index: 5246458 (Open Web Text)

Max Activating Token Index: 505

Text #7

Max Range: 3.3417. Min Range: -3.3417

Max Act: 3.1944. Min Act: -0.1700

Data Index: 7939181 (Open Web Text)

Max Activating Token Index: 138

Text #8

Max Range: 3.3417. Min Range: -3.3417

Max Act: 3.2055. Min Act: -0.1700

Data Index: 5014122 (Open Web Text)

Max Activating Token Index: 969

Text #9

Max Range: 3.3417. Min Range: -3.3417

Max Act: 3.2020. Min Act: -0.1700

Data Index: 2047063 (Open Web Text)

Max Activating Token Index: 708

Text #10

Max Range: 3.3417. Min Range: -3.3417

Max Act: 3.1977. Min Act: -0.1700

Data Index: 8684259 (Open Web Text)

Max Activating Token Index: 929

Text #11

Max Range: 3.3417. Min Range: -3.3417

Max Act: 3.1787. Min Act: -0.1700

Data Index: 7935142 (Open Web Text)

Max Activating Token Index: 921

Text #12

Max Range: 3.3417. Min Range: -3.3417

Max Act: 3.1733. Min Act: -0.1700

Data Index: 4803643 (Open Web Text)

Max Activating Token Index: 628

Text #13

Max Range: 3.3417. Min Range: -3.3417

Max Act: 3.1784. Min Act: -0.1700

Data Index: 5396975 (Open Web Text)

Max Activating Token Index: 917

Text #14

Max Range: 3.3417. Min Range: -3.3417

Max Act: 3.1963. Min Act: -0.1700

Data Index: 7424382 (Open Web Text)

Max Activating Token Index: 878

Text #15

Max Range: 3.3417. Min Range: -3.3417

Max Act: 3.1781. Min Act: -0.1700

Data Index: 747802 (Open Web Text)

Max Activating Token Index: 211

Text #16

Max Range: 3.3417. Min Range: -3.3417

Max Act: 3.1578. Min Act: -0.1700

Data Index: 2377668 (Open Web Text)

Max Activating Token Index: 454

Text #17

Max Range: 3.3417. Min Range: -3.3417

Max Act: 3.1735. Min Act: -0.1700

Data Index: 1934039 (Open Web Text)

Max Activating Token Index: 308

Text #18

Max Range: 3.3417. Min Range: -3.3417

Max Act: 3.1408. Min Act: -0.1700

Data Index: 6309979 (Open Web Text)

Max Activating Token Index: 476

Text #19

Max Range: 3.3417. Min Range: -3.3417

Max Act: 3.1435. Min Act: -0.1700

Data Index: 6419870 (Open Web Text)

Max Activating Token Index: 251