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

Dataset: Open Web Text

Neuron 1293 in Layer 0

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: 6.4812. Min Range: -6.4812

Max Act: 6.4812. Min Act: -0.1700

Data Index: 3666993 (Open Web Text)

Max Activating Token Index: 6

Text #1

Max Range: 6.4812. Min Range: -6.4812

Max Act: 6.4491. Min Act: -0.1700

Data Index: 1863515 (Open Web Text)

Max Activating Token Index: 3

Text #2

Max Range: 6.4812. Min Range: -6.4812

Max Act: 6.3281. Min Act: -0.1700

Data Index: 3231621 (Open Web Text)

Max Activating Token Index: 807

Text #3

Max Range: 6.4812. Min Range: -6.4812

Max Act: 6.3414. Min Act: -0.1700

Data Index: 3320166 (Open Web Text)

Max Activating Token Index: 8

Text #4

Max Range: 6.4812. Min Range: -6.4812

Max Act: 6.3458. Min Act: -0.1700

Data Index: 4969707 (Open Web Text)

Max Activating Token Index: 5

Text #5

Max Range: 6.4812. Min Range: -6.4812

Max Act: 6.3412. Min Act: -0.1700

Data Index: 5012167 (Open Web Text)

Max Activating Token Index: 6

Text #6

Max Range: 6.4812. Min Range: -6.4812

Max Act: 6.3158. Min Act: -0.1700

Data Index: 4200677 (Open Web Text)

Max Activating Token Index: 4

Text #7

Max Range: 6.4812. Min Range: -6.4812

Max Act: 6.3212. Min Act: -0.1700

Data Index: 3230535 (Open Web Text)

Max Activating Token Index: 9

Text #8

Max Range: 6.4812. Min Range: -6.4812

Max Act: 6.2950. Min Act: -0.1700

Data Index: 2647109 (Open Web Text)

Max Activating Token Index: 7

Text #9

Max Range: 6.4812. Min Range: -6.4812

Max Act: 6.3317. Min Act: -0.1700

Data Index: 4358136 (Open Web Text)

Max Activating Token Index: 721

Text #10

Max Range: 6.4812. Min Range: -6.4812

Max Act: 6.2630. Min Act: -0.1700

Data Index: 6125470 (Open Web Text)

Max Activating Token Index: 773

Text #11

Max Range: 6.4812. Min Range: -6.4812

Max Act: 6.2445. Min Act: -0.1700

Data Index: 3066153 (Open Web Text)

Max Activating Token Index: 767

Text #12

Max Range: 6.4812. Min Range: -6.4812

Max Act: 6.2777. Min Act: -0.1700

Data Index: 6499749 (Open Web Text)

Max Activating Token Index: 4

Text #13

Max Range: 6.4812. Min Range: -6.4812

Max Act: 6.2638. Min Act: -0.1700

Data Index: 8611815 (Open Web Text)

Max Activating Token Index: 5

Text #14

Max Range: 6.4812. Min Range: -6.4812

Max Act: 6.2389. Min Act: -0.1700

Data Index: 6061810 (Open Web Text)

Max Activating Token Index: 643

Text #15

Max Range: 6.4812. Min Range: -6.4812

Max Act: 6.2513. Min Act: -0.1700

Data Index: 5489151 (Open Web Text)

Max Activating Token Index: 1013

Text #16

Max Range: 6.4812. Min Range: -6.4812

Max Act: 6.2488. Min Act: -0.1700

Data Index: 3334116 (Open Web Text)

Max Activating Token Index: 990

Text #17

Max Range: 6.4812. Min Range: -6.4812

Max Act: 6.2443. Min Act: -0.1700

Data Index: 3482482 (Open Web Text)

Max Activating Token Index: 389

Text #18

Max Range: 6.4812. Min Range: -6.4812

Max Act: 6.2387. Min Act: -0.1700

Data Index: 4290348 (Open Web Text)

Max Activating Token Index: 4

Text #19

Max Range: 6.4812. Min Range: -6.4812

Max Act: 6.2471. Min Act: -0.1700

Data Index: 1552282 (Open Web Text)

Max Activating Token Index: 5