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

Dataset: Open Web Text

Neuron 2492 in Layer 6

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: 3.3121. Min Range: -3.3121

Max Act: 3.3121. Min Act: -0.1700

Data Index: 6003813 (Open Web Text)

Max Activating Token Index: 372

Text #1

Max Range: 3.3121. Min Range: -3.3121

Max Act: 3.2737. Min Act: -0.1700

Data Index: 8289939 (Open Web Text)

Max Activating Token Index: 323

Text #2

Max Range: 3.3121. Min Range: -3.3121

Max Act: 3.2455. Min Act: -0.1700

Data Index: 145225 (Open Web Text)

Max Activating Token Index: 1002

Text #3

Max Range: 3.3121. Min Range: -3.3121

Max Act: 3.1606. Min Act: -0.1700

Data Index: 8148599 (Open Web Text)

Max Activating Token Index: 333

Text #4

Max Range: 3.3121. Min Range: -3.3121

Max Act: 3.1275. Min Act: -0.1700

Data Index: 531003 (Open Web Text)

Max Activating Token Index: 109

Text #5

Max Range: 3.3121. Min Range: -3.3121

Max Act: 3.1267. Min Act: -0.1700

Data Index: 6675690 (Open Web Text)

Max Activating Token Index: 497

Text #6

Max Range: 3.3121. Min Range: -3.3121

Max Act: 3.1345. Min Act: -0.1700

Data Index: 2451373 (Open Web Text)

Max Activating Token Index: 876

Text #7

Max Range: 3.3121. Min Range: -3.3121

Max Act: 3.1518. Min Act: -0.1700

Data Index: 3103727 (Open Web Text)

Max Activating Token Index: 713

Text #8

Max Range: 3.3121. Min Range: -3.3121

Max Act: 3.1247. Min Act: -0.1700

Data Index: 8175060 (Open Web Text)

Max Activating Token Index: 164

Text #9

Max Range: 3.3121. Min Range: -3.3121

Max Act: 3.1115. Min Act: -0.1700

Data Index: 6568996 (Open Web Text)

Max Activating Token Index: 626

Text #10

Max Range: 3.3121. Min Range: -3.3121

Max Act: 3.0922. Min Act: -0.1700

Data Index: 3732737 (Open Web Text)

Max Activating Token Index: 946

Text #11

Max Range: 3.3121. Min Range: -3.3121

Max Act: 3.0723. Min Act: -0.1700

Data Index: 6538136 (Open Web Text)

Max Activating Token Index: 617

Text #12

Max Range: 3.3121. Min Range: -3.3121

Max Act: 3.0836. Min Act: -0.1700

Data Index: 7784722 (Open Web Text)

Max Activating Token Index: 755

Text #13

Max Range: 3.3121. Min Range: -3.3121

Max Act: 3.0913. Min Act: -0.1700

Data Index: 4166078 (Open Web Text)

Max Activating Token Index: 298

Text #14

Max Range: 3.3121. Min Range: -3.3121

Max Act: 3.0795. Min Act: -0.1700

Data Index: 2735083 (Open Web Text)

Max Activating Token Index: 584

Text #15

Max Range: 3.3121. Min Range: -3.3121

Max Act: 3.0577. Min Act: -0.1700

Data Index: 2981886 (Open Web Text)

Max Activating Token Index: 308

Text #16

Max Range: 3.3121. Min Range: -3.3121

Max Act: 3.0676. Min Act: -0.1700

Data Index: 8757274 (Open Web Text)

Max Activating Token Index: 606

Text #17

Max Range: 3.3121. Min Range: -3.3121

Max Act: 3.0676. Min Act: -0.1700

Data Index: 3103728 (Open Web Text)

Max Activating Token Index: 52

Text #18

Max Range: 3.3121. Min Range: -3.3121

Max Act: 3.0323. Min Act: -0.1700

Data Index: 1515522 (Open Web Text)

Max Activating Token Index: 707

Text #19

Max Range: 3.3121. Min Range: -3.3121

Max Act: 3.0526. Min Act: -0.1700

Data Index: 1656946 (Open Web Text)

Max Activating Token Index: 140