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

Dataset: Open Web Text

Neuron 1551 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: 3.3435. Min Range: -3.3435

Max Act: 3.3435. Min Act: -0.1700

Data Index: 8441749 (Open Web Text)

Max Activating Token Index: 441

Text #1

Max Range: 3.3435. Min Range: -3.3435

Max Act: 3.2877. Min Act: -0.1700

Data Index: 2982494 (Open Web Text)

Max Activating Token Index: 380

Text #2

Max Range: 3.3435. Min Range: -3.3435

Max Act: 3.2119. Min Act: -0.1700

Data Index: 6631392 (Open Web Text)

Max Activating Token Index: 852

Text #3

Max Range: 3.3435. Min Range: -3.3435

Max Act: 3.1994. Min Act: -0.1700

Data Index: 6570563 (Open Web Text)

Max Activating Token Index: 885

Text #4

Max Range: 3.3435. Min Range: -3.3435

Max Act: 3.2072. Min Act: -0.1700

Data Index: 1831791 (Open Web Text)

Max Activating Token Index: 406

Text #5

Max Range: 3.3435. Min Range: -3.3435

Max Act: 3.1829. Min Act: -0.1700

Data Index: 2061977 (Open Web Text)

Max Activating Token Index: 200

Text #6

Max Range: 3.3435. Min Range: -3.3435

Max Act: 3.1787. Min Act: -0.1700

Data Index: 1160598 (Open Web Text)

Max Activating Token Index: 101

Text #7

Max Range: 3.3435. Min Range: -3.3435

Max Act: 3.1789. Min Act: -0.1700

Data Index: 577843 (Open Web Text)

Max Activating Token Index: 430

Text #8

Max Range: 3.3435. Min Range: -3.3435

Max Act: 3.1590. Min Act: -0.1700

Data Index: 4338008 (Open Web Text)

Max Activating Token Index: 662

Text #9

Max Range: 3.3435. Min Range: -3.3435

Max Act: 3.1322. Min Act: -0.1700

Data Index: 7437240 (Open Web Text)

Max Activating Token Index: 490

Text #10

Max Range: 3.3435. Min Range: -3.3435

Max Act: 3.1590. Min Act: -0.1700

Data Index: 3971638 (Open Web Text)

Max Activating Token Index: 146

Text #11

Max Range: 3.3435. Min Range: -3.3435

Max Act: 3.1671. Min Act: -0.1700

Data Index: 2239663 (Open Web Text)

Max Activating Token Index: 607

Text #12

Max Range: 3.3435. Min Range: -3.3435

Max Act: 3.1773. Min Act: -0.1700

Data Index: 7136971 (Open Web Text)

Max Activating Token Index: 406

Text #13

Max Range: 3.3435. Min Range: -3.3435

Max Act: 3.1624. Min Act: -0.1700

Data Index: 2234149 (Open Web Text)

Max Activating Token Index: 447

Text #14

Max Range: 3.3435. Min Range: -3.3435

Max Act: 3.1713. Min Act: -0.1700

Data Index: 5576445 (Open Web Text)

Max Activating Token Index: 138

Text #15

Max Range: 3.3435. Min Range: -3.3435

Max Act: 3.1539. Min Act: -0.1700

Data Index: 3320924 (Open Web Text)

Max Activating Token Index: 402

Text #16

Max Range: 3.3435. Min Range: -3.3435

Max Act: 3.1515. Min Act: -0.1700

Data Index: 4986299 (Open Web Text)

Max Activating Token Index: 882

Text #17

Max Range: 3.3435. Min Range: -3.3435

Max Act: 3.1554. Min Act: -0.1700

Data Index: 6853729 (Open Web Text)

Max Activating Token Index: 1004

Text #18

Max Range: 3.3435. Min Range: -3.3435

Max Act: 3.1401. Min Act: -0.1700

Data Index: 6490786 (Open Web Text)

Max Activating Token Index: 975

Text #19

Max Range: 3.3435. Min Range: -3.3435

Max Act: 3.1318. Min Act: -0.1700

Data Index: 4810930 (Open Web Text)

Max Activating Token Index: 707