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

Dataset: Open Web Text

Neuron 2878 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: 2.4874. Min Range: -2.4874

Max Act: 2.4874. Min Act: -0.1700

Data Index: 6940025 (Open Web Text)

Max Activating Token Index: 701

Text #1

Max Range: 2.4874. Min Range: -2.4874

Max Act: 2.4701. Min Act: -0.1700

Data Index: 7311351 (Open Web Text)

Max Activating Token Index: 220

Text #2

Max Range: 2.4874. Min Range: -2.4874

Max Act: 2.4471. Min Act: -0.1700

Data Index: 7584347 (Open Web Text)

Max Activating Token Index: 966

Text #3

Max Range: 2.4874. Min Range: -2.4874

Max Act: 2.4165. Min Act: -0.1700

Data Index: 1297897 (Open Web Text)

Max Activating Token Index: 989

Text #4

Max Range: 2.4874. Min Range: -2.4874

Max Act: 2.4301. Min Act: -0.1700

Data Index: 2384788 (Open Web Text)

Max Activating Token Index: 742

Text #5

Max Range: 2.4874. Min Range: -2.4874

Max Act: 2.4033. Min Act: -0.1700

Data Index: 7719276 (Open Web Text)

Max Activating Token Index: 542

Text #6

Max Range: 2.4874. Min Range: -2.4874

Max Act: 2.4014. Min Act: -0.1700

Data Index: 6891000 (Open Web Text)

Max Activating Token Index: 422

Text #7

Max Range: 2.4874. Min Range: -2.4874

Max Act: 2.4027. Min Act: -0.1700

Data Index: 4582391 (Open Web Text)

Max Activating Token Index: 976

Text #8

Max Range: 2.4874. Min Range: -2.4874

Max Act: 2.3814. Min Act: -0.1700

Data Index: 356610 (Open Web Text)

Max Activating Token Index: 837

Text #9

Max Range: 2.4874. Min Range: -2.4874

Max Act: 2.3835. Min Act: -0.1700

Data Index: 2229643 (Open Web Text)

Max Activating Token Index: 972

Text #10

Max Range: 2.4874. Min Range: -2.4874

Max Act: 2.3552. Min Act: -0.1700

Data Index: 7686607 (Open Web Text)

Max Activating Token Index: 1001

Text #11

Max Range: 2.4874. Min Range: -2.4874

Max Act: 2.3604. Min Act: -0.1700

Data Index: 6861327 (Open Web Text)

Max Activating Token Index: 574

Text #12

Max Range: 2.4874. Min Range: -2.4874

Max Act: 2.3654. Min Act: -0.1700

Data Index: 4536716 (Open Web Text)

Max Activating Token Index: 307

Text #13

Max Range: 2.4874. Min Range: -2.4874

Max Act: 2.3556. Min Act: -0.1700

Data Index: 4244877 (Open Web Text)

Max Activating Token Index: 456

Text #14

Max Range: 2.4874. Min Range: -2.4874

Max Act: 2.3659. Min Act: -0.1700

Data Index: 6890998 (Open Web Text)

Max Activating Token Index: 599

Text #15

Max Range: 2.4874. Min Range: -2.4874

Max Act: 2.3429. Min Act: -0.1700

Data Index: 1297898 (Open Web Text)

Max Activating Token Index: 113

Text #16

Max Range: 2.4874. Min Range: -2.4874

Max Act: 2.3429. Min Act: -0.1700

Data Index: 7719277 (Open Web Text)

Max Activating Token Index: 13

Text #17

Max Range: 2.4874. Min Range: -2.4874

Max Act: 2.3485. Min Act: -0.1700

Data Index: 2122149 (Open Web Text)

Max Activating Token Index: 290

Text #18

Max Range: 2.4874. Min Range: -2.4874

Max Act: 2.3485. Min Act: -0.1700

Data Index: 4226569 (Open Web Text)

Max Activating Token Index: 291

Text #19

Max Range: 2.4874. Min Range: -2.4874

Max Act: 2.3577. Min Act: -0.1700

Data Index: 4734065 (Open Web Text)

Max Activating Token Index: 148