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

Dataset: Open Web Text

Neuron 1045 in Layer 3

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: 5.5227. Min Range: -5.5227

Max Act: 5.5227. Min Act: -0.1700

Data Index: 3503841 (Open Web Text)

Max Activating Token Index: 266

Text #1

Max Range: 5.5227. Min Range: -5.5227

Max Act: 5.5058. Min Act: -0.1700

Data Index: 6256125 (Open Web Text)

Max Activating Token Index: 500

Text #2

Max Range: 5.5227. Min Range: -5.5227

Max Act: 5.4310. Min Act: -0.1700

Data Index: 3750690 (Open Web Text)

Max Activating Token Index: 159

Text #3

Max Range: 5.5227. Min Range: -5.5227

Max Act: 5.4130. Min Act: -0.1700

Data Index: 1985777 (Open Web Text)

Max Activating Token Index: 820

Text #4

Max Range: 5.5227. Min Range: -5.5227

Max Act: 5.3893. Min Act: -0.1700

Data Index: 6667629 (Open Web Text)

Max Activating Token Index: 837

Text #5

Max Range: 5.5227. Min Range: -5.5227

Max Act: 5.3475. Min Act: -0.1700

Data Index: 3736020 (Open Web Text)

Max Activating Token Index: 566

Text #6

Max Range: 5.5227. Min Range: -5.5227

Max Act: 5.2859. Min Act: -0.1700

Data Index: 7146411 (Open Web Text)

Max Activating Token Index: 175

Text #7

Max Range: 5.5227. Min Range: -5.5227

Max Act: 5.2677. Min Act: -0.1700

Data Index: 6493219 (Open Web Text)

Max Activating Token Index: 815

Text #8

Max Range: 5.5227. Min Range: -5.5227

Max Act: 5.2656. Min Act: -0.1700

Data Index: 492160 (Open Web Text)

Max Activating Token Index: 63

Text #9

Max Range: 5.5227. Min Range: -5.5227

Max Act: 5.2816. Min Act: -0.1700

Data Index: 7624816 (Open Web Text)

Max Activating Token Index: 851

Text #10

Max Range: 5.5227. Min Range: -5.5227

Max Act: 5.2257. Min Act: -0.1700

Data Index: 1496583 (Open Web Text)

Max Activating Token Index: 895

Text #11

Max Range: 5.5227. Min Range: -5.5227

Max Act: 5.1929. Min Act: -0.1700

Data Index: 1517937 (Open Web Text)

Max Activating Token Index: 711

Text #12

Max Range: 5.5227. Min Range: -5.5227

Max Act: 5.2333. Min Act: -0.1700

Data Index: 2297764 (Open Web Text)

Max Activating Token Index: 101

Text #13

Max Range: 5.5227. Min Range: -5.5227

Max Act: 5.1777. Min Act: -0.1700

Data Index: 7695048 (Open Web Text)

Max Activating Token Index: 518

Text #14

Max Range: 5.5227. Min Range: -5.5227

Max Act: 5.1624. Min Act: -0.1700

Data Index: 4615506 (Open Web Text)

Max Activating Token Index: 463

Text #15

Max Range: 5.5227. Min Range: -5.5227

Max Act: 5.1329. Min Act: -0.1700

Data Index: 6266851 (Open Web Text)

Max Activating Token Index: 423

Text #16

Max Range: 5.5227. Min Range: -5.5227

Max Act: 5.1463. Min Act: -0.1700

Data Index: 1169706 (Open Web Text)

Max Activating Token Index: 123

Text #17

Max Range: 5.5227. Min Range: -5.5227

Max Act: 5.1209. Min Act: -0.1700

Data Index: 2524642 (Open Web Text)

Max Activating Token Index: 392

Text #18

Max Range: 5.5227. Min Range: -5.5227

Max Act: 5.0869. Min Act: -0.1700

Data Index: 5004416 (Open Web Text)

Max Activating Token Index: 92

Text #19

Max Range: 5.5227. Min Range: -5.5227

Max Act: 5.0818. Min Act: -0.1700

Data Index: 2907636 (Open Web Text)

Max Activating Token Index: 415