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

Dataset: Open Web Text

Neuron 424 in Layer 2

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: 3.9628. Min Range: -3.9628

Max Act: 3.9628. Min Act: -0.1700

Data Index: 4785951 (Open Web Text)

Max Activating Token Index: 83

Text #1

Max Range: 3.9628. Min Range: -3.9628

Max Act: 3.8682. Min Act: -0.1700

Data Index: 625479 (Open Web Text)

Max Activating Token Index: 991

Text #2

Max Range: 3.9628. Min Range: -3.9628

Max Act: 3.8965. Min Act: -0.1700

Data Index: 1474978 (Open Web Text)

Max Activating Token Index: 572

Text #3

Max Range: 3.9628. Min Range: -3.9628

Max Act: 3.8681. Min Act: -0.1700

Data Index: 4419831 (Open Web Text)

Max Activating Token Index: 71

Text #4

Max Range: 3.9628. Min Range: -3.9628

Max Act: 3.7789. Min Act: -0.1700

Data Index: 7896242 (Open Web Text)

Max Activating Token Index: 564

Text #5

Max Range: 3.9628. Min Range: -3.9628

Max Act: 3.7545. Min Act: -0.1700

Data Index: 7163334 (Open Web Text)

Max Activating Token Index: 96

Text #6

Max Range: 3.9628. Min Range: -3.9628

Max Act: 3.7447. Min Act: -0.1700

Data Index: 915228 (Open Web Text)

Max Activating Token Index: 633

Text #7

Max Range: 3.9628. Min Range: -3.9628

Max Act: 3.7179. Min Act: -0.1700

Data Index: 8711474 (Open Web Text)

Max Activating Token Index: 138

Text #8

Max Range: 3.9628. Min Range: -3.9628

Max Act: 3.7064. Min Act: -0.1700

Data Index: 3078216 (Open Web Text)

Max Activating Token Index: 374

Text #9

Max Range: 3.9628. Min Range: -3.9628

Max Act: 3.6697. Min Act: -0.1700

Data Index: 1099005 (Open Web Text)

Max Activating Token Index: 394

Text #10

Max Range: 3.9628. Min Range: -3.9628

Max Act: 3.6801. Min Act: -0.1700

Data Index: 3870440 (Open Web Text)

Max Activating Token Index: 122

Text #11

Max Range: 3.9628. Min Range: -3.9628

Max Act: 3.6632. Min Act: -0.1700

Data Index: 6490239 (Open Web Text)

Max Activating Token Index: 161

Text #12

Max Range: 3.9628. Min Range: -3.9628

Max Act: 3.6424. Min Act: -0.1700

Data Index: 8225963 (Open Web Text)

Max Activating Token Index: 155

Text #13

Max Range: 3.9628. Min Range: -3.9628

Max Act: 3.6206. Min Act: -0.1700

Data Index: 6205581 (Open Web Text)

Max Activating Token Index: 114

Text #14

Max Range: 3.9628. Min Range: -3.9628

Max Act: 3.5964. Min Act: -0.1700

Data Index: 8832558 (Open Web Text)

Max Activating Token Index: 165

Text #15

Max Range: 3.9628. Min Range: -3.9628

Max Act: 3.6161. Min Act: -0.1700

Data Index: 1609043 (Open Web Text)

Max Activating Token Index: 103

Text #16

Max Range: 3.9628. Min Range: -3.9628

Max Act: 3.5671. Min Act: -0.1700

Data Index: 5167041 (Open Web Text)

Max Activating Token Index: 188

Text #17

Max Range: 3.9628. Min Range: -3.9628

Max Act: 3.5340. Min Act: -0.1700

Data Index: 3317972 (Open Web Text)

Max Activating Token Index: 148

Text #18

Max Range: 3.9628. Min Range: -3.9628

Max Act: 3.5731. Min Act: -0.1700

Data Index: 1903130 (Open Web Text)

Max Activating Token Index: 740

Text #19

Max Range: 3.9628. Min Range: -3.9628

Max Act: 3.5686. Min Act: -0.1700

Data Index: 2521644 (Open Web Text)

Max Activating Token Index: 483