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

Dataset: Open Web Text

Neuron 944 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: 3.2835. Min Range: -3.2835

Max Act: 3.2785. Min Act: -0.1700

Data Index: 2612101 (Open Web Text)

Max Activating Token Index: 150

Text #1

Max Range: 3.2835. Min Range: -3.2835

Max Act: 3.2835. Min Act: -0.1700

Data Index: 5452586 (Open Web Text)

Max Activating Token Index: 350

Text #2

Max Range: 3.2835. Min Range: -3.2835

Max Act: 3.1968. Min Act: -0.1700

Data Index: 5499232 (Open Web Text)

Max Activating Token Index: 731

Text #3

Max Range: 3.2835. Min Range: -3.2835

Max Act: 3.1926. Min Act: -0.1700

Data Index: 8182785 (Open Web Text)

Max Activating Token Index: 311

Text #4

Max Range: 3.2835. Min Range: -3.2835

Max Act: 3.1839. Min Act: -0.1700

Data Index: 1812963 (Open Web Text)

Max Activating Token Index: 650

Text #5

Max Range: 3.2835. Min Range: -3.2835

Max Act: 3.1742. Min Act: -0.1700

Data Index: 4213346 (Open Web Text)

Max Activating Token Index: 563

Text #6

Max Range: 3.2835. Min Range: -3.2835

Max Act: 3.0997. Min Act: -0.1700

Data Index: 3002344 (Open Web Text)

Max Activating Token Index: 263

Text #7

Max Range: 3.2835. Min Range: -3.2835

Max Act: 3.0677. Min Act: -0.1700

Data Index: 6299242 (Open Web Text)

Max Activating Token Index: 931

Text #8

Max Range: 3.2835. Min Range: -3.2835

Max Act: 3.0634. Min Act: -0.1700

Data Index: 690955 (Open Web Text)

Max Activating Token Index: 192

Text #9

Max Range: 3.2835. Min Range: -3.2835

Max Act: 3.0785. Min Act: -0.1700

Data Index: 3889275 (Open Web Text)

Max Activating Token Index: 1001

Text #10

Max Range: 3.2835. Min Range: -3.2835

Max Act: 3.0507. Min Act: -0.1700

Data Index: 4404187 (Open Web Text)

Max Activating Token Index: 503

Text #11

Max Range: 3.2835. Min Range: -3.2835

Max Act: 3.0390. Min Act: -0.1700

Data Index: 1044295 (Open Web Text)

Max Activating Token Index: 105

Text #12

Max Range: 3.2835. Min Range: -3.2835

Max Act: 3.0315. Min Act: -0.1700

Data Index: 3339127 (Open Web Text)

Max Activating Token Index: 407

Text #13

Max Range: 3.2835. Min Range: -3.2835

Max Act: 3.0172. Min Act: -0.1700

Data Index: 1451548 (Open Web Text)

Max Activating Token Index: 274

Text #14

Max Range: 3.2835. Min Range: -3.2835

Max Act: 3.0226. Min Act: -0.1700

Data Index: 5285554 (Open Web Text)

Max Activating Token Index: 698

Text #15

Max Range: 3.2835. Min Range: -3.2835

Max Act: 3.0056. Min Act: -0.1700

Data Index: 5952872 (Open Web Text)

Max Activating Token Index: 332

Text #16

Max Range: 3.2835. Min Range: -3.2835

Max Act: 2.9793. Min Act: -0.1700

Data Index: 6097100 (Open Web Text)

Max Activating Token Index: 442

Text #17

Max Range: 3.2835. Min Range: -3.2835

Max Act: 2.9862. Min Act: -0.1700

Data Index: 7176785 (Open Web Text)

Max Activating Token Index: 681

Text #18

Max Range: 3.2835. Min Range: -3.2835

Max Act: 3.0039. Min Act: -0.1700

Data Index: 5744477 (Open Web Text)

Max Activating Token Index: 331

Text #19

Max Range: 3.2835. Min Range: -3.2835

Max Act: 2.9733. Min Act: -0.1700

Data Index: 3375487 (Open Web Text)

Max Activating Token Index: 968