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

Dataset: Open Web Text

Neuron 2829 in Layer 3

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: 3.3680. Min Range: -3.3680

Max Act: 3.3626. Min Act: -0.1700

Data Index: 5103831 (Open Web Text)

Max Activating Token Index: 318

Text #1

Max Range: 3.3680. Min Range: -3.3680

Max Act: 3.3342. Min Act: -0.1700

Data Index: 6188450 (Open Web Text)

Max Activating Token Index: 234

Text #2

Max Range: 3.3680. Min Range: -3.3680

Max Act: 3.2988. Min Act: -0.1700

Data Index: 759390 (Open Web Text)

Max Activating Token Index: 473

Text #3

Max Range: 3.3680. Min Range: -3.3680

Max Act: 3.3680. Min Act: -0.1700

Data Index: 7435647 (Open Web Text)

Max Activating Token Index: 814

Text #4

Max Range: 3.3680. Min Range: -3.3680

Max Act: 3.2907. Min Act: -0.1700

Data Index: 4204439 (Open Web Text)

Max Activating Token Index: 400

Text #5

Max Range: 3.3680. Min Range: -3.3680

Max Act: 3.2694. Min Act: -0.1700

Data Index: 3371882 (Open Web Text)

Max Activating Token Index: 174

Text #6

Max Range: 3.3680. Min Range: -3.3680

Max Act: 3.3065. Min Act: -0.1700

Data Index: 4145812 (Open Web Text)

Max Activating Token Index: 9

Text #7

Max Range: 3.3680. Min Range: -3.3680

Max Act: 3.2916. Min Act: -0.1700

Data Index: 7845355 (Open Web Text)

Max Activating Token Index: 174

Text #8

Max Range: 3.3680. Min Range: -3.3680

Max Act: 3.2746. Min Act: -0.1700

Data Index: 3371891 (Open Web Text)

Max Activating Token Index: 187

Text #9

Max Range: 3.3680. Min Range: -3.3680

Max Act: 3.2754. Min Act: -0.1700

Data Index: 3371900 (Open Web Text)

Max Activating Token Index: 172

Text #10

Max Range: 3.3680. Min Range: -3.3680

Max Act: 3.2348. Min Act: -0.1700

Data Index: 585548 (Open Web Text)

Max Activating Token Index: 641

Text #11

Max Range: 3.3680. Min Range: -3.3680

Max Act: 3.2536. Min Act: -0.1700

Data Index: 1870959 (Open Web Text)

Max Activating Token Index: 17

Text #12

Max Range: 3.3680. Min Range: -3.3680

Max Act: 3.2313. Min Act: -0.1700

Data Index: 567098 (Open Web Text)

Max Activating Token Index: 451

Text #13

Max Range: 3.3680. Min Range: -3.3680

Max Act: 3.1726. Min Act: -0.1700

Data Index: 8077236 (Open Web Text)

Max Activating Token Index: 778

Text #14

Max Range: 3.3680. Min Range: -3.3680

Max Act: 3.2397. Min Act: -0.1700

Data Index: 42207 (Open Web Text)

Max Activating Token Index: 8

Text #15

Max Range: 3.3680. Min Range: -3.3680

Max Act: 3.1951. Min Act: -0.1700

Data Index: 8045498 (Open Web Text)

Max Activating Token Index: 982

Text #16

Max Range: 3.3680. Min Range: -3.3680

Max Act: 3.2364. Min Act: -0.1700

Data Index: 3371886 (Open Web Text)

Max Activating Token Index: 692

Text #17

Max Range: 3.3680. Min Range: -3.3680

Max Act: 3.1961. Min Act: -0.1700

Data Index: 5044798 (Open Web Text)

Max Activating Token Index: 349

Text #18

Max Range: 3.3680. Min Range: -3.3680

Max Act: 3.1910. Min Act: -0.1700

Data Index: 8009187 (Open Web Text)

Max Activating Token Index: 53

Text #19

Max Range: 3.3680. Min Range: -3.3680

Max Act: 3.2324. Min Act: -0.1700

Data Index: 3808834 (Open Web Text)

Max Activating Token Index: 238