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

Dataset: Open Web Text

Neuron 968 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: 6.9024. Min Range: -6.9024

Max Act: 6.8771. Min Act: -0.1700

Data Index: 4793744 (Open Web Text)

Max Activating Token Index: 668

Text #1

Max Range: 6.9024. Min Range: -6.9024

Max Act: 6.9024. Min Act: -0.1700

Data Index: 8671885 (Open Web Text)

Max Activating Token Index: 361

Text #2

Max Range: 6.9024. Min Range: -6.9024

Max Act: 6.8663. Min Act: -0.1700

Data Index: 7714684 (Open Web Text)

Max Activating Token Index: 263

Text #3

Max Range: 6.9024. Min Range: -6.9024

Max Act: 6.8279. Min Act: -0.1700

Data Index: 3173360 (Open Web Text)

Max Activating Token Index: 96

Text #4

Max Range: 6.9024. Min Range: -6.9024

Max Act: 6.8016. Min Act: -0.1700

Data Index: 7529754 (Open Web Text)

Max Activating Token Index: 434

Text #5

Max Range: 6.9024. Min Range: -6.9024

Max Act: 6.7349. Min Act: -0.1700

Data Index: 8733084 (Open Web Text)

Max Activating Token Index: 689

Text #6

Max Range: 6.9024. Min Range: -6.9024

Max Act: 6.8053. Min Act: -0.1700

Data Index: 7187008 (Open Web Text)

Max Activating Token Index: 935

Text #7

Max Range: 6.9024. Min Range: -6.9024

Max Act: 6.7029. Min Act: -0.1700

Data Index: 7297690 (Open Web Text)

Max Activating Token Index: 200

Text #8

Max Range: 6.9024. Min Range: -6.9024

Max Act: 6.7351. Min Act: -0.1700

Data Index: 6845114 (Open Web Text)

Max Activating Token Index: 612

Text #9

Max Range: 6.9024. Min Range: -6.9024

Max Act: 6.6858. Min Act: -0.1700

Data Index: 4521193 (Open Web Text)

Max Activating Token Index: 366

Text #10

Max Range: 6.9024. Min Range: -6.9024

Max Act: 6.6659. Min Act: -0.1700

Data Index: 2086410 (Open Web Text)

Max Activating Token Index: 929

Text #11

Max Range: 6.9024. Min Range: -6.9024

Max Act: 6.7031. Min Act: -0.1700

Data Index: 3523056 (Open Web Text)

Max Activating Token Index: 135

Text #12

Max Range: 6.9024. Min Range: -6.9024

Max Act: 6.6687. Min Act: -0.1700

Data Index: 2812650 (Open Web Text)

Max Activating Token Index: 580

Text #13

Max Range: 6.9024. Min Range: -6.9024

Max Act: 6.6548. Min Act: -0.1700

Data Index: 7651300 (Open Web Text)

Max Activating Token Index: 593

Text #14

Max Range: 6.9024. Min Range: -6.9024

Max Act: 6.5978. Min Act: -0.1700

Data Index: 3484577 (Open Web Text)

Max Activating Token Index: 761

Text #15

Max Range: 6.9024. Min Range: -6.9024

Max Act: 6.5984. Min Act: -0.1700

Data Index: 1779245 (Open Web Text)

Max Activating Token Index: 423

Text #16

Max Range: 6.9024. Min Range: -6.9024

Max Act: 6.5946. Min Act: -0.1700

Data Index: 4319953 (Open Web Text)

Max Activating Token Index: 811

Text #17

Max Range: 6.9024. Min Range: -6.9024

Max Act: 6.5820. Min Act: -0.1700

Data Index: 3483802 (Open Web Text)

Max Activating Token Index: 742

Text #18

Max Range: 6.9024. Min Range: -6.9024

Max Act: 6.5196. Min Act: -0.1700

Data Index: 4916210 (Open Web Text)

Max Activating Token Index: 679

Text #19

Max Range: 6.9024. Min Range: -6.9024

Max Act: 6.5924. Min Act: -0.1700

Data Index: 4396616 (Open Web Text)

Max Activating Token Index: 455