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

Dataset: Open Web Text

Neuron 935 in Layer 4

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: 2.0979. Min Range: -2.0979

Max Act: 2.0867. Min Act: -0.1699

Data Index: 6224468 (Open Web Text)

Max Activating Token Index: 880

Text #1

Max Range: 2.0979. Min Range: -2.0979

Max Act: 2.0979. Min Act: -0.1700

Data Index: 4851755 (Open Web Text)

Max Activating Token Index: 454

Text #2

Max Range: 2.0979. Min Range: -2.0979

Max Act: 2.0695. Min Act: -0.1699

Data Index: 8642636 (Open Web Text)

Max Activating Token Index: 655

Text #3

Max Range: 2.0979. Min Range: -2.0979

Max Act: 2.0646. Min Act: -0.1700

Data Index: 2153352 (Open Web Text)

Max Activating Token Index: 301

Text #4

Max Range: 2.0979. Min Range: -2.0979

Max Act: 2.0784. Min Act: -0.1700

Data Index: 5520163 (Open Web Text)

Max Activating Token Index: 9

Text #5

Max Range: 2.0979. Min Range: -2.0979

Max Act: 2.0772. Min Act: -0.1700

Data Index: 5455859 (Open Web Text)

Max Activating Token Index: 429

Text #6

Max Range: 2.0979. Min Range: -2.0979

Max Act: 2.0644. Min Act: -0.1700

Data Index: 8171142 (Open Web Text)

Max Activating Token Index: 503

Text #7

Max Range: 2.0979. Min Range: -2.0979

Max Act: 2.0360. Min Act: -0.1700

Data Index: 7456974 (Open Web Text)

Max Activating Token Index: 593

Text #8

Max Range: 2.0979. Min Range: -2.0979

Max Act: 2.0488. Min Act: -0.1700

Data Index: 879194 (Open Web Text)

Max Activating Token Index: 116

Text #9

Max Range: 2.0979. Min Range: -2.0979

Max Act: 2.0400. Min Act: -0.1700

Data Index: 3673538 (Open Web Text)

Max Activating Token Index: 897

Text #10

Max Range: 2.0979. Min Range: -2.0979

Max Act: 2.0437. Min Act: -0.1700

Data Index: 6253136 (Open Web Text)

Max Activating Token Index: 13

Text #11

Max Range: 2.0979. Min Range: -2.0979

Max Act: 2.0430. Min Act: -0.1700

Data Index: 3066249 (Open Web Text)

Max Activating Token Index: 15

Text #12

Max Range: 2.0979. Min Range: -2.0979

Max Act: 2.0483. Min Act: -0.1700

Data Index: 6076077 (Open Web Text)

Max Activating Token Index: 357

Text #13

Max Range: 2.0979. Min Range: -2.0979

Max Act: 2.0513. Min Act: -0.1700

Data Index: 5411126 (Open Web Text)

Max Activating Token Index: 575

Text #14

Max Range: 2.0979. Min Range: -2.0979

Max Act: 2.0149. Min Act: -0.1700

Data Index: 7980186 (Open Web Text)

Max Activating Token Index: 10

Text #15

Max Range: 2.0979. Min Range: -2.0979

Max Act: 1.9992. Min Act: -0.1700

Data Index: 2049349 (Open Web Text)

Max Activating Token Index: 13

Text #16

Max Range: 2.0979. Min Range: -2.0979

Max Act: 1.9949. Min Act: -0.1700

Data Index: 7115275 (Open Web Text)

Max Activating Token Index: 761

Text #17

Max Range: 2.0979. Min Range: -2.0979

Max Act: 1.9842. Min Act: -0.1700

Data Index: 8026359 (Open Web Text)

Max Activating Token Index: 255

Text #18

Max Range: 2.0979. Min Range: -2.0979

Max Act: 2.0018. Min Act: -0.1700

Data Index: 2594773 (Open Web Text)

Max Activating Token Index: 555

Text #19

Max Range: 2.0979. Min Range: -2.0979

Max Act: 1.9969. Min Act: -0.1700

Data Index: 4637166 (Open Web Text)

Max Activating Token Index: 15