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

Dataset: Open Web Text

Neuron 1585 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: 2.0924. Min Range: -2.0924

Max Act: 2.0924. Min Act: -0.1557

Data Index: 143286 (Open Web Text)

Max Activating Token Index: 363

Text #1

Max Range: 2.0924. Min Range: -2.0924

Max Act: 2.0775. Min Act: -0.1700

Data Index: 1768158 (Open Web Text)

Max Activating Token Index: 959

Text #2

Max Range: 2.0924. Min Range: -2.0924

Max Act: 2.0697. Min Act: -0.1698

Data Index: 1195351 (Open Web Text)

Max Activating Token Index: 448

Text #3

Max Range: 2.0924. Min Range: -2.0924

Max Act: 2.0510. Min Act: -0.1698

Data Index: 1768155 (Open Web Text)

Max Activating Token Index: 903

Text #4

Max Range: 2.0924. Min Range: -2.0924

Max Act: 2.0292. Min Act: -0.1696

Data Index: 789720 (Open Web Text)

Max Activating Token Index: 75

Text #5

Max Range: 2.0924. Min Range: -2.0924

Max Act: 2.0242. Min Act: -0.1700

Data Index: 1579081 (Open Web Text)

Max Activating Token Index: 60

Text #6

Max Range: 2.0924. Min Range: -2.0924

Max Act: 2.0082. Min Act: -0.1700

Data Index: 8407835 (Open Web Text)

Max Activating Token Index: 130

Text #7

Max Range: 2.0924. Min Range: -2.0924

Max Act: 2.0045. Min Act: -0.1693

Data Index: 5822322 (Open Web Text)

Max Activating Token Index: 178

Text #8

Max Range: 2.0924. Min Range: -2.0924

Max Act: 1.9997. Min Act: -0.1697

Data Index: 2085811 (Open Web Text)

Max Activating Token Index: 775

Text #9

Max Range: 2.0924. Min Range: -2.0924

Max Act: 1.9973. Min Act: -0.1697

Data Index: 4439521 (Open Web Text)

Max Activating Token Index: 173

Text #10

Max Range: 2.0924. Min Range: -2.0924

Max Act: 2.0011. Min Act: -0.1700

Data Index: 7401293 (Open Web Text)

Max Activating Token Index: 844

Text #11

Max Range: 2.0924. Min Range: -2.0924

Max Act: 1.9815. Min Act: -0.1697

Data Index: 4758196 (Open Web Text)

Max Activating Token Index: 76

Text #12

Max Range: 2.0924. Min Range: -2.0924

Max Act: 1.9781. Min Act: -0.1700

Data Index: 659682 (Open Web Text)

Max Activating Token Index: 409

Text #13

Max Range: 2.0924. Min Range: -2.0924

Max Act: 1.9865. Min Act: -0.1696

Data Index: 4569261 (Open Web Text)

Max Activating Token Index: 473

Text #14

Max Range: 2.0924. Min Range: -2.0924

Max Act: 1.9900. Min Act: -0.1700

Data Index: 4563554 (Open Web Text)

Max Activating Token Index: 106

Text #15

Max Range: 2.0924. Min Range: -2.0924

Max Act: 1.9744. Min Act: -0.1700

Data Index: 3448131 (Open Web Text)

Max Activating Token Index: 411

Text #16

Max Range: 2.0924. Min Range: -2.0924

Max Act: 1.9765. Min Act: -0.1700

Data Index: 7532201 (Open Web Text)

Max Activating Token Index: 367

Text #17

Max Range: 2.0924. Min Range: -2.0924

Max Act: 1.9727. Min Act: -0.1695

Data Index: 6590081 (Open Web Text)

Max Activating Token Index: 352

Text #18

Max Range: 2.0924. Min Range: -2.0924

Max Act: 1.9747. Min Act: -0.1698

Data Index: 6881152 (Open Web Text)

Max Activating Token Index: 55

Text #19

Max Range: 2.0924. Min Range: -2.0924

Max Act: 1.9713. Min Act: -0.1700

Data Index: 6998546 (Open Web Text)

Max Activating Token Index: 265