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

Dataset: Open Web Text

Neuron 776 in Layer 6

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: 3.3638. Min Range: -3.3638

Max Act: 3.3509. Min Act: -0.1700

Data Index: 502221 (Open Web Text)

Max Activating Token Index: 918

Text #1

Max Range: 3.3638. Min Range: -3.3638

Max Act: 3.3638. Min Act: -0.1700

Data Index: 7106858 (Open Web Text)

Max Activating Token Index: 914

Text #2

Max Range: 3.3638. Min Range: -3.3638

Max Act: 3.3183. Min Act: -0.1700

Data Index: 8106801 (Open Web Text)

Max Activating Token Index: 294

Text #3

Max Range: 3.3638. Min Range: -3.3638

Max Act: 3.2401. Min Act: -0.1700

Data Index: 449322 (Open Web Text)

Max Activating Token Index: 682

Text #4

Max Range: 3.3638. Min Range: -3.3638

Max Act: 3.2405. Min Act: -0.1700

Data Index: 1054927 (Open Web Text)

Max Activating Token Index: 614

Text #5

Max Range: 3.3638. Min Range: -3.3638

Max Act: 3.2263. Min Act: -0.1700

Data Index: 1593601 (Open Web Text)

Max Activating Token Index: 671

Text #6

Max Range: 3.3638. Min Range: -3.3638

Max Act: 3.2044. Min Act: -0.1700

Data Index: 7463278 (Open Web Text)

Max Activating Token Index: 492

Text #7

Max Range: 3.3638. Min Range: -3.3638

Max Act: 3.2044. Min Act: -0.1700

Data Index: 2706088 (Open Web Text)

Max Activating Token Index: 500

Text #8

Max Range: 3.3638. Min Range: -3.3638

Max Act: 3.1759. Min Act: -0.1700

Data Index: 2807469 (Open Web Text)

Max Activating Token Index: 671

Text #9

Max Range: 3.3638. Min Range: -3.3638

Max Act: 3.1901. Min Act: -0.1700

Data Index: 1127895 (Open Web Text)

Max Activating Token Index: 223

Text #10

Max Range: 3.3638. Min Range: -3.3638

Max Act: 3.1850. Min Act: -0.1700

Data Index: 4432830 (Open Web Text)

Max Activating Token Index: 965

Text #11

Max Range: 3.3638. Min Range: -3.3638

Max Act: 3.1629. Min Act: -0.1700

Data Index: 189122 (Open Web Text)

Max Activating Token Index: 387

Text #12

Max Range: 3.3638. Min Range: -3.3638

Max Act: 3.1582. Min Act: -0.1700

Data Index: 8728172 (Open Web Text)

Max Activating Token Index: 458

Text #13

Max Range: 3.3638. Min Range: -3.3638

Max Act: 3.1651. Min Act: -0.1700

Data Index: 1643449 (Open Web Text)

Max Activating Token Index: 698

Text #14

Max Range: 3.3638. Min Range: -3.3638

Max Act: 3.1373. Min Act: -0.1700

Data Index: 7935301 (Open Web Text)

Max Activating Token Index: 379

Text #15

Max Range: 3.3638. Min Range: -3.3638

Max Act: 3.1398. Min Act: -0.1700

Data Index: 745419 (Open Web Text)

Max Activating Token Index: 437

Text #16

Max Range: 3.3638. Min Range: -3.3638

Max Act: 3.1417. Min Act: -0.1700

Data Index: 7857801 (Open Web Text)

Max Activating Token Index: 707

Text #17

Max Range: 3.3638. Min Range: -3.3638

Max Act: 3.1352. Min Act: -0.1700

Data Index: 3664608 (Open Web Text)

Max Activating Token Index: 282

Text #18

Max Range: 3.3638. Min Range: -3.3638

Max Act: 3.1196. Min Act: -0.1700

Data Index: 6811615 (Open Web Text)

Max Activating Token Index: 990

Text #19

Max Range: 3.3638. Min Range: -3.3638

Max Act: 3.0927. Min Act: -0.1700

Data Index: 7838524 (Open Web Text)

Max Activating Token Index: 449