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

Dataset: Open Web Text

Neuron 2023 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: 3.6260. Min Range: -3.6260

Max Act: 3.6260. Min Act: -0.1700

Data Index: 6587014 (Open Web Text)

Max Activating Token Index: 657

Text #1

Max Range: 3.6260. Min Range: -3.6260

Max Act: 3.5682. Min Act: -0.1700

Data Index: 8531493 (Open Web Text)

Max Activating Token Index: 921

Text #2

Max Range: 3.6260. Min Range: -3.6260

Max Act: 3.6025. Min Act: -0.1700

Data Index: 6092259 (Open Web Text)

Max Activating Token Index: 754

Text #3

Max Range: 3.6260. Min Range: -3.6260

Max Act: 3.5739. Min Act: -0.1700

Data Index: 8708702 (Open Web Text)

Max Activating Token Index: 1005

Text #4

Max Range: 3.6260. Min Range: -3.6260

Max Act: 3.5675. Min Act: -0.1700

Data Index: 4846562 (Open Web Text)

Max Activating Token Index: 1013

Text #5

Max Range: 3.6260. Min Range: -3.6260

Max Act: 3.4874. Min Act: -0.1700

Data Index: 4444092 (Open Web Text)

Max Activating Token Index: 190

Text #6

Max Range: 3.6260. Min Range: -3.6260

Max Act: 3.5220. Min Act: -0.1700

Data Index: 7176231 (Open Web Text)

Max Activating Token Index: 449

Text #7

Max Range: 3.6260. Min Range: -3.6260

Max Act: 3.4667. Min Act: -0.1700

Data Index: 1353242 (Open Web Text)

Max Activating Token Index: 354

Text #8

Max Range: 3.6260. Min Range: -3.6260

Max Act: 3.5042. Min Act: -0.1700

Data Index: 251564 (Open Web Text)

Max Activating Token Index: 426

Text #9

Max Range: 3.6260. Min Range: -3.6260

Max Act: 3.4921. Min Act: -0.1700

Data Index: 2598067 (Open Web Text)

Max Activating Token Index: 544

Text #10

Max Range: 3.6260. Min Range: -3.6260

Max Act: 3.5109. Min Act: -0.1700

Data Index: 5903596 (Open Web Text)

Max Activating Token Index: 704

Text #11

Max Range: 3.6260. Min Range: -3.6260

Max Act: 3.4893. Min Act: -0.1700

Data Index: 4868264 (Open Web Text)

Max Activating Token Index: 267

Text #12

Max Range: 3.6260. Min Range: -3.6260

Max Act: 3.4442. Min Act: -0.1700

Data Index: 1011357 (Open Web Text)

Max Activating Token Index: 458

Text #13

Max Range: 3.6260. Min Range: -3.6260

Max Act: 3.4518. Min Act: -0.1700

Data Index: 3714171 (Open Web Text)

Max Activating Token Index: 514

Text #14

Max Range: 3.6260. Min Range: -3.6260

Max Act: 3.4677. Min Act: -0.1700

Data Index: 2086644 (Open Web Text)

Max Activating Token Index: 962

Text #15

Max Range: 3.6260. Min Range: -3.6260

Max Act: 3.4546. Min Act: -0.1700

Data Index: 4996434 (Open Web Text)

Max Activating Token Index: 168

Text #16

Max Range: 3.6260. Min Range: -3.6260

Max Act: 3.4600. Min Act: -0.1700

Data Index: 2620347 (Open Web Text)

Max Activating Token Index: 222

Text #17

Max Range: 3.6260. Min Range: -3.6260

Max Act: 3.4302. Min Act: -0.1700

Data Index: 1618936 (Open Web Text)

Max Activating Token Index: 470

Text #18

Max Range: 3.6260. Min Range: -3.6260

Max Act: 3.4348. Min Act: -0.1700

Data Index: 236567 (Open Web Text)

Max Activating Token Index: 108

Text #19

Max Range: 3.6260. Min Range: -3.6260

Max Act: 3.4328. Min Act: -0.1700

Data Index: 7197013 (Open Web Text)

Max Activating Token Index: 466