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

Dataset: Open Web Text

Neuron 1962 in Layer 0

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: 2.5426. Min Range: -2.5426

Max Act: 2.5426. Min Act: -0.1700

Data Index: 3291115 (Open Web Text)

Max Activating Token Index: 2

Text #1

Max Range: 2.5426. Min Range: -2.5426

Max Act: 2.5426. Min Act: -0.1700

Data Index: 6640076 (Open Web Text)

Max Activating Token Index: 2

Text #2

Max Range: 2.5426. Min Range: -2.5426

Max Act: 2.4979. Min Act: -0.1700

Data Index: 6370280 (Open Web Text)

Max Activating Token Index: 4

Text #3

Max Range: 2.5426. Min Range: -2.5426

Max Act: 2.4861. Min Act: -0.1700

Data Index: 7663761 (Open Web Text)

Max Activating Token Index: 4

Text #4

Max Range: 2.5426. Min Range: -2.5426

Max Act: 2.4770. Min Act: -0.1700

Data Index: 8361937 (Open Web Text)

Max Activating Token Index: 42

Text #5

Max Range: 2.5426. Min Range: -2.5426

Max Act: 2.4751. Min Act: -0.1700

Data Index: 8415734 (Open Web Text)

Max Activating Token Index: 5

Text #6

Max Range: 2.5426. Min Range: -2.5426

Max Act: 2.4523. Min Act: -0.1700

Data Index: 2324713 (Open Web Text)

Max Activating Token Index: 2

Text #7

Max Range: 2.5426. Min Range: -2.5426

Max Act: 2.4589. Min Act: -0.1700

Data Index: 1468669 (Open Web Text)

Max Activating Token Index: 22

Text #8

Max Range: 2.5426. Min Range: -2.5426

Max Act: 2.4648. Min Act: -0.1700

Data Index: 7620966 (Open Web Text)

Max Activating Token Index: 5

Text #9

Max Range: 2.5426. Min Range: -2.5426

Max Act: 2.4669. Min Act: -0.1700

Data Index: 4930856 (Open Web Text)

Max Activating Token Index: 9

Text #10

Max Range: 2.5426. Min Range: -2.5426

Max Act: 2.4693. Min Act: -0.1700

Data Index: 3692835 (Open Web Text)

Max Activating Token Index: 2

Text #11

Max Range: 2.5426. Min Range: -2.5426

Max Act: 2.4693. Min Act: -0.1700

Data Index: 7272158 (Open Web Text)

Max Activating Token Index: 2

Text #12

Max Range: 2.5426. Min Range: -2.5426

Max Act: 2.4516. Min Act: -0.1700

Data Index: 4715661 (Open Web Text)

Max Activating Token Index: 5

Text #13

Max Range: 2.5426. Min Range: -2.5426

Max Act: 2.4523. Min Act: -0.1700

Data Index: 1636503 (Open Web Text)

Max Activating Token Index: 2

Text #14

Max Range: 2.5426. Min Range: -2.5426

Max Act: 2.4443. Min Act: -0.1700

Data Index: 7198639 (Open Web Text)

Max Activating Token Index: 941

Text #15

Max Range: 2.5426. Min Range: -2.5426

Max Act: 2.4399. Min Act: -0.1700

Data Index: 6735225 (Open Web Text)

Max Activating Token Index: 12

Text #16

Max Range: 2.5426. Min Range: -2.5426

Max Act: 2.4525. Min Act: -0.1700

Data Index: 5735541 (Open Web Text)

Max Activating Token Index: 3

Text #17

Max Range: 2.5426. Min Range: -2.5426

Max Act: 2.4444. Min Act: -0.1700

Data Index: 7141999 (Open Web Text)

Max Activating Token Index: 4

Text #18

Max Range: 2.5426. Min Range: -2.5426

Max Act: 2.4231. Min Act: -0.1700

Data Index: 5255835 (Open Web Text)

Max Activating Token Index: 79

Text #19

Max Range: 2.5426. Min Range: -2.5426

Max Act: 2.4251. Min Act: -0.1700

Data Index: 6730274 (Open Web Text)

Max Activating Token Index: 4