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

Dataset: Open Web Text

Neuron 263 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: 4.5923. Min Range: -4.5923

Max Act: 4.5923. Min Act: -0.1700

Data Index: 4025858 (Open Web Text)

Max Activating Token Index: 7

Text #1

Max Range: 4.5923. Min Range: -4.5923

Max Act: 4.5671. Min Act: -0.1700

Data Index: 3101463 (Open Web Text)

Max Activating Token Index: 3

Text #2

Max Range: 4.5923. Min Range: -4.5923

Max Act: 4.5593. Min Act: -0.1700

Data Index: 5722754 (Open Web Text)

Max Activating Token Index: 3

Text #3

Max Range: 4.5923. Min Range: -4.5923

Max Act: 4.5417. Min Act: -0.1700

Data Index: 7244318 (Open Web Text)

Max Activating Token Index: 3

Text #4

Max Range: 4.5923. Min Range: -4.5923

Max Act: 4.5500. Min Act: -0.1700

Data Index: 8296427 (Open Web Text)

Max Activating Token Index: 5

Text #5

Max Range: 4.5923. Min Range: -4.5923

Max Act: 4.4846. Min Act: -0.1700

Data Index: 5138353 (Open Web Text)

Max Activating Token Index: 800

Text #6

Max Range: 4.5923. Min Range: -4.5923

Max Act: 4.5063. Min Act: -0.1700

Data Index: 969688 (Open Web Text)

Max Activating Token Index: 7

Text #7

Max Range: 4.5923. Min Range: -4.5923

Max Act: 4.4886. Min Act: -0.1700

Data Index: 8528507 (Open Web Text)

Max Activating Token Index: 3

Text #8

Max Range: 4.5923. Min Range: -4.5923

Max Act: 4.4797. Min Act: -0.1700

Data Index: 633738 (Open Web Text)

Max Activating Token Index: 7

Text #9

Max Range: 4.5923. Min Range: -4.5923

Max Act: 4.4684. Min Act: -0.1700

Data Index: 1338755 (Open Web Text)

Max Activating Token Index: 4

Text #10

Max Range: 4.5923. Min Range: -4.5923

Max Act: 4.4653. Min Act: -0.1700

Data Index: 2114344 (Open Web Text)

Max Activating Token Index: 3

Text #11

Max Range: 4.5923. Min Range: -4.5923

Max Act: 4.4660. Min Act: -0.1700

Data Index: 2133027 (Open Web Text)

Max Activating Token Index: 3

Text #12

Max Range: 4.5923. Min Range: -4.5923

Max Act: 4.4629. Min Act: -0.1700

Data Index: 4514363 (Open Web Text)

Max Activating Token Index: 3

Text #13

Max Range: 4.5923. Min Range: -4.5923

Max Act: 4.4607. Min Act: -0.1700

Data Index: 2314914 (Open Web Text)

Max Activating Token Index: 3

Text #14

Max Range: 4.5923. Min Range: -4.5923

Max Act: 4.4635. Min Act: -0.1700

Data Index: 2731794 (Open Web Text)

Max Activating Token Index: 3

Text #15

Max Range: 4.5923. Min Range: -4.5923

Max Act: 4.4575. Min Act: -0.1699

Data Index: 1530658 (Open Web Text)

Max Activating Token Index: 4

Text #16

Max Range: 4.5923. Min Range: -4.5923

Max Act: 4.4527. Min Act: -0.1700

Data Index: 4537367 (Open Web Text)

Max Activating Token Index: 4

Text #17

Max Range: 4.5923. Min Range: -4.5923

Max Act: 4.4638. Min Act: -0.1700

Data Index: 1024161 (Open Web Text)

Max Activating Token Index: 5

Text #18

Max Range: 4.5923. Min Range: -4.5923

Max Act: 4.4728. Min Act: -0.1700

Data Index: 702350 (Open Web Text)

Max Activating Token Index: 3

Text #19

Max Range: 4.5923. Min Range: -4.5923

Max Act: 4.4868. Min Act: -0.1700

Data Index: 5028685 (Open Web Text)

Max Activating Token Index: 7