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

Dataset: Open Web Text

Neuron 1977 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: 3.5718. Min Range: -3.5718

Max Act: 3.5718. Min Act: -0.1700

Data Index: 4646890 (Open Web Text)

Max Activating Token Index: 602

Text #1

Max Range: 3.5718. Min Range: -3.5718

Max Act: 3.5552. Min Act: -0.1700

Data Index: 7452272 (Open Web Text)

Max Activating Token Index: 343

Text #2

Max Range: 3.5718. Min Range: -3.5718

Max Act: 3.5627. Min Act: -0.1700

Data Index: 802103 (Open Web Text)

Max Activating Token Index: 764

Text #3

Max Range: 3.5718. Min Range: -3.5718

Max Act: 3.5428. Min Act: -0.1700

Data Index: 8373052 (Open Web Text)

Max Activating Token Index: 165

Text #4

Max Range: 3.5718. Min Range: -3.5718

Max Act: 3.5241. Min Act: -0.1700

Data Index: 71016 (Open Web Text)

Max Activating Token Index: 415

Text #5

Max Range: 3.5718. Min Range: -3.5718

Max Act: 3.4943. Min Act: -0.1700

Data Index: 1237377 (Open Web Text)

Max Activating Token Index: 395

Text #6

Max Range: 3.5718. Min Range: -3.5718

Max Act: 3.5022. Min Act: -0.1700

Data Index: 8108866 (Open Web Text)

Max Activating Token Index: 753

Text #7

Max Range: 3.5718. Min Range: -3.5718

Max Act: 3.4920. Min Act: -0.1700

Data Index: 324765 (Open Web Text)

Max Activating Token Index: 341

Text #8

Max Range: 3.5718. Min Range: -3.5718

Max Act: 3.4991. Min Act: -0.1700

Data Index: 1320564 (Open Web Text)

Max Activating Token Index: 69

Text #9

Max Range: 3.5718. Min Range: -3.5718

Max Act: 3.4745. Min Act: -0.1700

Data Index: 1982777 (Open Web Text)

Max Activating Token Index: 563

Text #10

Max Range: 3.5718. Min Range: -3.5718

Max Act: 3.4719. Min Act: -0.1700

Data Index: 6182467 (Open Web Text)

Max Activating Token Index: 400

Text #11

Max Range: 3.5718. Min Range: -3.5718

Max Act: 3.4670. Min Act: -0.1700

Data Index: 7766397 (Open Web Text)

Max Activating Token Index: 249

Text #12

Max Range: 3.5718. Min Range: -3.5718

Max Act: 3.4813. Min Act: -0.1700

Data Index: 4332891 (Open Web Text)

Max Activating Token Index: 214

Text #13

Max Range: 3.5718. Min Range: -3.5718

Max Act: 3.4631. Min Act: -0.1700

Data Index: 2533778 (Open Web Text)

Max Activating Token Index: 352

Text #14

Max Range: 3.5718. Min Range: -3.5718

Max Act: 3.4618. Min Act: -0.1700

Data Index: 7952915 (Open Web Text)

Max Activating Token Index: 940

Text #15

Max Range: 3.5718. Min Range: -3.5718

Max Act: 3.4687. Min Act: -0.1700

Data Index: 4723506 (Open Web Text)

Max Activating Token Index: 28

Text #16

Max Range: 3.5718. Min Range: -3.5718

Max Act: 3.4751. Min Act: -0.1700

Data Index: 5252106 (Open Web Text)

Max Activating Token Index: 492

Text #17

Max Range: 3.5718. Min Range: -3.5718

Max Act: 3.4489. Min Act: -0.1700

Data Index: 3223685 (Open Web Text)

Max Activating Token Index: 359

Text #18

Max Range: 3.5718. Min Range: -3.5718

Max Act: 3.4616. Min Act: -0.1700

Data Index: 1280746 (Open Web Text)

Max Activating Token Index: 4

Text #19

Max Range: 3.5718. Min Range: -3.5718

Max Act: 3.4298. Min Act: -0.1700

Data Index: 5549757 (Open Web Text)

Max Activating Token Index: 508