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

Dataset: Open Web Text

Neuron 1669 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: 2.4435. Min Range: -2.4435

Max Act: 2.4435. Min Act: -0.1697

Data Index: 2176880 (Open Web Text)

Max Activating Token Index: 420

Text #1

Max Range: 2.4435. Min Range: -2.4435

Max Act: 2.4354. Min Act: -0.1700

Data Index: 1650199 (Open Web Text)

Max Activating Token Index: 966

Text #2

Max Range: 2.4435. Min Range: -2.4435

Max Act: 2.4345. Min Act: -0.1700

Data Index: 5432207 (Open Web Text)

Max Activating Token Index: 1008

Text #3

Max Range: 2.4435. Min Range: -2.4435

Max Act: 2.3937. Min Act: -0.1700

Data Index: 2299271 (Open Web Text)

Max Activating Token Index: 14

Text #4

Max Range: 2.4435. Min Range: -2.4435

Max Act: 2.3911. Min Act: -0.1700

Data Index: 7171533 (Open Web Text)

Max Activating Token Index: 655

Text #5

Max Range: 2.4435. Min Range: -2.4435

Max Act: 2.3904. Min Act: -0.1700

Data Index: 5960107 (Open Web Text)

Max Activating Token Index: 446

Text #6

Max Range: 2.4435. Min Range: -2.4435

Max Act: 2.3667. Min Act: -0.1700

Data Index: 1706852 (Open Web Text)

Max Activating Token Index: 142

Text #7

Max Range: 2.4435. Min Range: -2.4435

Max Act: 2.3619. Min Act: -0.1692

Data Index: 1015149 (Open Web Text)

Max Activating Token Index: 472

Text #8

Max Range: 2.4435. Min Range: -2.4435

Max Act: 2.3585. Min Act: -0.1699

Data Index: 5073537 (Open Web Text)

Max Activating Token Index: 378

Text #9

Max Range: 2.4435. Min Range: -2.4435

Max Act: 2.3483. Min Act: -0.1700

Data Index: 2314845 (Open Web Text)

Max Activating Token Index: 160

Text #10

Max Range: 2.4435. Min Range: -2.4435

Max Act: 2.3323. Min Act: -0.1700

Data Index: 446131 (Open Web Text)

Max Activating Token Index: 161

Text #11

Max Range: 2.4435. Min Range: -2.4435

Max Act: 2.3429. Min Act: -0.1700

Data Index: 7061856 (Open Web Text)

Max Activating Token Index: 835

Text #12

Max Range: 2.4435. Min Range: -2.4435

Max Act: 2.3419. Min Act: -0.1700

Data Index: 7928857 (Open Web Text)

Max Activating Token Index: 374

Text #13

Max Range: 2.4435. Min Range: -2.4435

Max Act: 2.3129. Min Act: -0.1489

Data Index: 5432208 (Open Web Text)

Max Activating Token Index: 697

Text #14

Max Range: 2.4435. Min Range: -2.4435

Max Act: 2.3257. Min Act: -0.1700

Data Index: 7433487 (Open Web Text)

Max Activating Token Index: 117

Text #15

Max Range: 2.4435. Min Range: -2.4435

Max Act: 2.3254. Min Act: -0.1700

Data Index: 190200 (Open Web Text)

Max Activating Token Index: 808

Text #16

Max Range: 2.4435. Min Range: -2.4435

Max Act: 2.3048. Min Act: -0.1700

Data Index: 1561443 (Open Web Text)

Max Activating Token Index: 143

Text #17

Max Range: 2.4435. Min Range: -2.4435

Max Act: 2.2948. Min Act: -0.1700

Data Index: 1019841 (Open Web Text)

Max Activating Token Index: 612

Text #18

Max Range: 2.4435. Min Range: -2.4435

Max Act: 2.2909. Min Act: -0.1700

Data Index: 770513 (Open Web Text)

Max Activating Token Index: 717

Text #19

Max Range: 2.4435. Min Range: -2.4435

Max Act: 2.3049. Min Act: -0.1700

Data Index: 6814962 (Open Web Text)

Max Activating Token Index: 97