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

Dataset: Open Web Text

Neuron 1937 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: 3.1627. Min Range: -3.1627

Max Act: 3.1627. Min Act: -0.1700

Data Index: 5422660 (Open Web Text)

Max Activating Token Index: 33

Text #1

Max Range: 3.1627. Min Range: -3.1627

Max Act: 2.9586. Min Act: -0.1700

Data Index: 766733 (Open Web Text)

Max Activating Token Index: 27

Text #2

Max Range: 3.1627. Min Range: -3.1627

Max Act: 2.9332. Min Act: -0.1700

Data Index: 4598345 (Open Web Text)

Max Activating Token Index: 29

Text #3

Max Range: 3.1627. Min Range: -3.1627

Max Act: 2.9193. Min Act: -0.1700

Data Index: 1796529 (Open Web Text)

Max Activating Token Index: 395

Text #4

Max Range: 3.1627. Min Range: -3.1627

Max Act: 2.9153. Min Act: -0.1700

Data Index: 2373346 (Open Web Text)

Max Activating Token Index: 646

Text #5

Max Range: 3.1627. Min Range: -3.1627

Max Act: 2.8886. Min Act: -0.1700

Data Index: 7522164 (Open Web Text)

Max Activating Token Index: 558

Text #6

Max Range: 3.1627. Min Range: -3.1627

Max Act: 2.8868. Min Act: -0.1700

Data Index: 155316 (Open Web Text)

Max Activating Token Index: 663

Text #7

Max Range: 3.1627. Min Range: -3.1627

Max Act: 2.8894. Min Act: -0.1700

Data Index: 3320035 (Open Web Text)

Max Activating Token Index: 242

Text #8

Max Range: 3.1627. Min Range: -3.1627

Max Act: 2.8785. Min Act: -0.1700

Data Index: 517138 (Open Web Text)

Max Activating Token Index: 220

Text #9

Max Range: 3.1627. Min Range: -3.1627

Max Act: 2.8773. Min Act: -0.1700

Data Index: 8232199 (Open Web Text)

Max Activating Token Index: 965

Text #10

Max Range: 3.1627. Min Range: -3.1627

Max Act: 2.8637. Min Act: -0.1700

Data Index: 5520969 (Open Web Text)

Max Activating Token Index: 296

Text #11

Max Range: 3.1627. Min Range: -3.1627

Max Act: 2.8593. Min Act: -0.1700

Data Index: 6088198 (Open Web Text)

Max Activating Token Index: 799

Text #12

Max Range: 3.1627. Min Range: -3.1627

Max Act: 2.8489. Min Act: -0.1700

Data Index: 6918830 (Open Web Text)

Max Activating Token Index: 456

Text #13

Max Range: 3.1627. Min Range: -3.1627

Max Act: 2.8740. Min Act: -0.1700

Data Index: 2546976 (Open Web Text)

Max Activating Token Index: 80

Text #14

Max Range: 3.1627. Min Range: -3.1627

Max Act: 2.8693. Min Act: -0.1700

Data Index: 2329040 (Open Web Text)

Max Activating Token Index: 23

Text #15

Max Range: 3.1627. Min Range: -3.1627

Max Act: 2.8618. Min Act: -0.1700

Data Index: 8496018 (Open Web Text)

Max Activating Token Index: 580

Text #16

Max Range: 3.1627. Min Range: -3.1627

Max Act: 2.8518. Min Act: -0.1700

Data Index: 3230649 (Open Web Text)

Max Activating Token Index: 38

Text #17

Max Range: 3.1627. Min Range: -3.1627

Max Act: 2.8562. Min Act: -0.1700

Data Index: 5107440 (Open Web Text)

Max Activating Token Index: 320

Text #18

Max Range: 3.1627. Min Range: -3.1627

Max Act: 2.8644. Min Act: -0.1700

Data Index: 4314783 (Open Web Text)

Max Activating Token Index: 1015

Text #19

Max Range: 3.1627. Min Range: -3.1627

Max Act: 2.8598. Min Act: -0.1700

Data Index: 4619142 (Open Web Text)

Max Activating Token Index: 462