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

Dataset: Open Web Text

Neuron 2912 in Layer 4

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: 3.2603. Min Range: -3.2603

Max Act: 3.2554. Min Act: -0.1700

Data Index: 3522918 (Open Web Text)

Max Activating Token Index: 487

Text #1

Max Range: 3.2603. Min Range: -3.2603

Max Act: 3.2603. Min Act: -0.1700

Data Index: 8030851 (Open Web Text)

Max Activating Token Index: 763

Text #2

Max Range: 3.2603. Min Range: -3.2603

Max Act: 3.2134. Min Act: -0.1700

Data Index: 1264544 (Open Web Text)

Max Activating Token Index: 838

Text #3

Max Range: 3.2603. Min Range: -3.2603

Max Act: 3.2095. Min Act: -0.1700

Data Index: 6921234 (Open Web Text)

Max Activating Token Index: 491

Text #4

Max Range: 3.2603. Min Range: -3.2603

Max Act: 3.2094. Min Act: -0.1700

Data Index: 6217656 (Open Web Text)

Max Activating Token Index: 173

Text #5

Max Range: 3.2603. Min Range: -3.2603

Max Act: 3.1878. Min Act: -0.1700

Data Index: 1901038 (Open Web Text)

Max Activating Token Index: 462

Text #6

Max Range: 3.2603. Min Range: -3.2603

Max Act: 3.2132. Min Act: -0.1700

Data Index: 6853581 (Open Web Text)

Max Activating Token Index: 927

Text #7

Max Range: 3.2603. Min Range: -3.2603

Max Act: 3.1706. Min Act: -0.1700

Data Index: 3619012 (Open Web Text)

Max Activating Token Index: 480

Text #8

Max Range: 3.2603. Min Range: -3.2603

Max Act: 3.1733. Min Act: -0.1700

Data Index: 1654202 (Open Web Text)

Max Activating Token Index: 908

Text #9

Max Range: 3.2603. Min Range: -3.2603

Max Act: 3.1502. Min Act: -0.1700

Data Index: 3052138 (Open Web Text)

Max Activating Token Index: 506

Text #10

Max Range: 3.2603. Min Range: -3.2603

Max Act: 3.1554. Min Act: -0.1700

Data Index: 2133143 (Open Web Text)

Max Activating Token Index: 525

Text #11

Max Range: 3.2603. Min Range: -3.2603

Max Act: 3.1245. Min Act: -0.1700

Data Index: 8276479 (Open Web Text)

Max Activating Token Index: 751

Text #12

Max Range: 3.2603. Min Range: -3.2603

Max Act: 3.1441. Min Act: -0.1700

Data Index: 8087214 (Open Web Text)

Max Activating Token Index: 210

Text #13

Max Range: 3.2603. Min Range: -3.2603

Max Act: 3.1446. Min Act: -0.1700

Data Index: 1500497 (Open Web Text)

Max Activating Token Index: 205

Text #14

Max Range: 3.2603. Min Range: -3.2603

Max Act: 3.1481. Min Act: -0.1700

Data Index: 5062939 (Open Web Text)

Max Activating Token Index: 176

Text #15

Max Range: 3.2603. Min Range: -3.2603

Max Act: 3.1294. Min Act: -0.1700

Data Index: 1007118 (Open Web Text)

Max Activating Token Index: 624

Text #16

Max Range: 3.2603. Min Range: -3.2603

Max Act: 3.1585. Min Act: -0.1700

Data Index: 4611555 (Open Web Text)

Max Activating Token Index: 357

Text #17

Max Range: 3.2603. Min Range: -3.2603

Max Act: 3.1515. Min Act: -0.1700

Data Index: 1387773 (Open Web Text)

Max Activating Token Index: 512

Text #18

Max Range: 3.2603. Min Range: -3.2603

Max Act: 3.1588. Min Act: -0.1700

Data Index: 6423520 (Open Web Text)

Max Activating Token Index: 383

Text #19

Max Range: 3.2603. Min Range: -3.2603

Max Act: 3.1780. Min Act: -0.1700

Data Index: 5339700 (Open Web Text)

Max Activating Token Index: 246