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

Dataset: Open Web Text

Neuron 2613 in Layer 5

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: 4.9376. Min Range: -4.9376

Max Act: 4.9338. Min Act: -0.1700

Data Index: 908276 (Open Web Text)

Max Activating Token Index: 611

Text #1

Max Range: 4.9376. Min Range: -4.9376

Max Act: 4.9376. Min Act: -0.1700

Data Index: 2697829 (Open Web Text)

Max Activating Token Index: 377

Text #2

Max Range: 4.9376. Min Range: -4.9376

Max Act: 4.8988. Min Act: -0.1700

Data Index: 5398198 (Open Web Text)

Max Activating Token Index: 239

Text #3

Max Range: 4.9376. Min Range: -4.9376

Max Act: 4.8497. Min Act: -0.1700

Data Index: 3677286 (Open Web Text)

Max Activating Token Index: 312

Text #4

Max Range: 4.9376. Min Range: -4.9376

Max Act: 4.8313. Min Act: -0.1700

Data Index: 3206392 (Open Web Text)

Max Activating Token Index: 568

Text #5

Max Range: 4.9376. Min Range: -4.9376

Max Act: 4.8273. Min Act: -0.1700

Data Index: 5974850 (Open Web Text)

Max Activating Token Index: 720

Text #6

Max Range: 4.9376. Min Range: -4.9376

Max Act: 4.8121. Min Act: -0.1700

Data Index: 6476340 (Open Web Text)

Max Activating Token Index: 464

Text #7

Max Range: 4.9376. Min Range: -4.9376

Max Act: 4.8326. Min Act: -0.1700

Data Index: 5974856 (Open Web Text)

Max Activating Token Index: 760

Text #8

Max Range: 4.9376. Min Range: -4.9376

Max Act: 4.8381. Min Act: -0.1700

Data Index: 8541056 (Open Web Text)

Max Activating Token Index: 559

Text #9

Max Range: 4.9376. Min Range: -4.9376

Max Act: 4.8134. Min Act: -0.1700

Data Index: 7164625 (Open Web Text)

Max Activating Token Index: 482

Text #10

Max Range: 4.9376. Min Range: -4.9376

Max Act: 4.7983. Min Act: -0.1700

Data Index: 1174039 (Open Web Text)

Max Activating Token Index: 205

Text #11

Max Range: 4.9376. Min Range: -4.9376

Max Act: 4.7312. Min Act: -0.1700

Data Index: 919123 (Open Web Text)

Max Activating Token Index: 387

Text #12

Max Range: 4.9376. Min Range: -4.9376

Max Act: 4.7427. Min Act: -0.1700

Data Index: 8573609 (Open Web Text)

Max Activating Token Index: 359

Text #13

Max Range: 4.9376. Min Range: -4.9376

Max Act: 4.7354. Min Act: -0.1700

Data Index: 3459324 (Open Web Text)

Max Activating Token Index: 189

Text #14

Max Range: 4.9376. Min Range: -4.9376

Max Act: 4.7575. Min Act: -0.1700

Data Index: 1256486 (Open Web Text)

Max Activating Token Index: 595

Text #15

Max Range: 4.9376. Min Range: -4.9376

Max Act: 4.7082. Min Act: -0.1700

Data Index: 4358672 (Open Web Text)

Max Activating Token Index: 616

Text #16

Max Range: 4.9376. Min Range: -4.9376

Max Act: 4.7344. Min Act: -0.1700

Data Index: 4190088 (Open Web Text)

Max Activating Token Index: 993

Text #17

Max Range: 4.9376. Min Range: -4.9376

Max Act: 4.6978. Min Act: -0.1700

Data Index: 2828421 (Open Web Text)

Max Activating Token Index: 574

Text #18

Max Range: 4.9376. Min Range: -4.9376

Max Act: 4.7459. Min Act: -0.1700

Data Index: 8513127 (Open Web Text)

Max Activating Token Index: 869

Text #19

Max Range: 4.9376. Min Range: -4.9376

Max Act: 4.6806. Min Act: -0.1700

Data Index: 1692528 (Open Web Text)

Max Activating Token Index: 233