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

Dataset: Open Web Text

Neuron 1093 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: 1.6445. Min Range: -1.6445

Max Act: 1.6445. Min Act: -0.1700

Data Index: 6711280 (Open Web Text)

Max Activating Token Index: 316

Text #1

Max Range: 1.6445. Min Range: -1.6445

Max Act: 1.6412. Min Act: -0.1700

Data Index: 2932505 (Open Web Text)

Max Activating Token Index: 964

Text #2

Max Range: 1.6445. Min Range: -1.6445

Max Act: 1.6279. Min Act: -0.1700

Data Index: 2678727 (Open Web Text)

Max Activating Token Index: 491

Text #3

Max Range: 1.6445. Min Range: -1.6445

Max Act: 1.6127. Min Act: -0.1700

Data Index: 4201875 (Open Web Text)

Max Activating Token Index: 341

Text #4

Max Range: 1.6445. Min Range: -1.6445

Max Act: 1.6078. Min Act: -0.1698

Data Index: 7607619 (Open Web Text)

Max Activating Token Index: 263

Text #5

Max Range: 1.6445. Min Range: -1.6445

Max Act: 1.5988. Min Act: -0.1700

Data Index: 7617888 (Open Web Text)

Max Activating Token Index: 490

Text #6

Max Range: 1.6445. Min Range: -1.6445

Max Act: 1.5962. Min Act: -0.1700

Data Index: 4882294 (Open Web Text)

Max Activating Token Index: 551

Text #7

Max Range: 1.6445. Min Range: -1.6445

Max Act: 1.5792. Min Act: -0.1700

Data Index: 2303918 (Open Web Text)

Max Activating Token Index: 356

Text #8

Max Range: 1.6445. Min Range: -1.6445

Max Act: 1.5852. Min Act: -0.1700

Data Index: 2092352 (Open Web Text)

Max Activating Token Index: 115

Text #9

Max Range: 1.6445. Min Range: -1.6445

Max Act: 1.5656. Min Act: -0.1700

Data Index: 3076565 (Open Web Text)

Max Activating Token Index: 133

Text #10

Max Range: 1.6445. Min Range: -1.6445

Max Act: 1.5631. Min Act: -0.1700

Data Index: 8252924 (Open Web Text)

Max Activating Token Index: 47

Text #11

Max Range: 1.6445. Min Range: -1.6445

Max Act: 1.5696. Min Act: -0.1700

Data Index: 3479490 (Open Web Text)

Max Activating Token Index: 526

Text #12

Max Range: 1.6445. Min Range: -1.6445

Max Act: 1.5616. Min Act: -0.1700

Data Index: 890990 (Open Web Text)

Max Activating Token Index: 502

Text #13

Max Range: 1.6445. Min Range: -1.6445

Max Act: 1.5516. Min Act: -0.1700

Data Index: 1613910 (Open Web Text)

Max Activating Token Index: 72

Text #14

Max Range: 1.6445. Min Range: -1.6445

Max Act: 1.5673. Min Act: -0.1700

Data Index: 7582670 (Open Web Text)

Max Activating Token Index: 581

Text #15

Max Range: 1.6445. Min Range: -1.6445

Max Act: 1.5561. Min Act: -0.1700

Data Index: 7568732 (Open Web Text)

Max Activating Token Index: 1022

Text #16

Max Range: 1.6445. Min Range: -1.6445

Max Act: 1.5582. Min Act: -0.1700

Data Index: 4488253 (Open Web Text)

Max Activating Token Index: 456

Text #17

Max Range: 1.6445. Min Range: -1.6445

Max Act: 1.5589. Min Act: -0.1700

Data Index: 7753105 (Open Web Text)

Max Activating Token Index: 152

Text #18

Max Range: 1.6445. Min Range: -1.6445

Max Act: 1.5591. Min Act: -0.1700

Data Index: 3041713 (Open Web Text)

Max Activating Token Index: 352

Text #19

Max Range: 1.6445. Min Range: -1.6445

Max Act: 1.5432. Min Act: -0.1700

Data Index: 205730 (Open Web Text)

Max Activating Token Index: 438