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

Dataset: Open Web Text

Neuron 517 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: 3.3480. Min Range: -3.3480

Max Act: 3.3480. Min Act: -0.1700

Data Index: 5813971 (Open Web Text)

Max Activating Token Index: 1007

Text #1

Max Range: 3.3480. Min Range: -3.3480

Max Act: 3.3319. Min Act: -0.1700

Data Index: 2537803 (Open Web Text)

Max Activating Token Index: 952

Text #2

Max Range: 3.3480. Min Range: -3.3480

Max Act: 3.3099. Min Act: -0.1700

Data Index: 4785937 (Open Web Text)

Max Activating Token Index: 638

Text #3

Max Range: 3.3480. Min Range: -3.3480

Max Act: 3.2602. Min Act: -0.1700

Data Index: 7115797 (Open Web Text)

Max Activating Token Index: 349

Text #4

Max Range: 3.3480. Min Range: -3.3480

Max Act: 3.2371. Min Act: -0.1700

Data Index: 3073571 (Open Web Text)

Max Activating Token Index: 410

Text #5

Max Range: 3.3480. Min Range: -3.3480

Max Act: 3.2479. Min Act: -0.1700

Data Index: 4376365 (Open Web Text)

Max Activating Token Index: 384

Text #6

Max Range: 3.3480. Min Range: -3.3480

Max Act: 3.2505. Min Act: -0.1700

Data Index: 7311577 (Open Web Text)

Max Activating Token Index: 929

Text #7

Max Range: 3.3480. Min Range: -3.3480

Max Act: 3.2242. Min Act: -0.1700

Data Index: 2160646 (Open Web Text)

Max Activating Token Index: 209

Text #8

Max Range: 3.3480. Min Range: -3.3480

Max Act: 3.2365. Min Act: -0.1700

Data Index: 5575530 (Open Web Text)

Max Activating Token Index: 423

Text #9

Max Range: 3.3480. Min Range: -3.3480

Max Act: 3.2152. Min Act: -0.1700

Data Index: 8419527 (Open Web Text)

Max Activating Token Index: 721

Text #10

Max Range: 3.3480. Min Range: -3.3480

Max Act: 3.2121. Min Act: -0.1700

Data Index: 5446666 (Open Web Text)

Max Activating Token Index: 579

Text #11

Max Range: 3.3480. Min Range: -3.3480

Max Act: 3.2074. Min Act: -0.1700

Data Index: 713799 (Open Web Text)

Max Activating Token Index: 792

Text #12

Max Range: 3.3480. Min Range: -3.3480

Max Act: 3.2071. Min Act: -0.1700

Data Index: 1367087 (Open Web Text)

Max Activating Token Index: 231

Text #13

Max Range: 3.3480. Min Range: -3.3480

Max Act: 3.1953. Min Act: -0.1700

Data Index: 3127870 (Open Web Text)

Max Activating Token Index: 268

Text #14

Max Range: 3.3480. Min Range: -3.3480

Max Act: 3.1969. Min Act: -0.1700

Data Index: 3159299 (Open Web Text)

Max Activating Token Index: 412

Text #15

Max Range: 3.3480. Min Range: -3.3480

Max Act: 3.2024. Min Act: -0.1700

Data Index: 7647789 (Open Web Text)

Max Activating Token Index: 888

Text #16

Max Range: 3.3480. Min Range: -3.3480

Max Act: 3.1716. Min Act: -0.1700

Data Index: 4009389 (Open Web Text)

Max Activating Token Index: 739

Text #17

Max Range: 3.3480. Min Range: -3.3480

Max Act: 3.1746. Min Act: -0.1700

Data Index: 7707563 (Open Web Text)

Max Activating Token Index: 355

Text #18

Max Range: 3.3480. Min Range: -3.3480

Max Act: 3.1921. Min Act: -0.1700

Data Index: 2326367 (Open Web Text)

Max Activating Token Index: 315

Text #19

Max Range: 3.3480. Min Range: -3.3480

Max Act: 3.1782. Min Act: -0.1700

Data Index: 1907447 (Open Web Text)

Max Activating Token Index: 651