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

Dataset: Open Web Text

Neuron 281 in Layer 2

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: 3.4785. Min Range: -3.4785

Max Act: 3.4785. Min Act: -0.1700

Data Index: 1720055 (Open Web Text)

Max Activating Token Index: 834

Text #1

Max Range: 3.4785. Min Range: -3.4785

Max Act: 3.3977. Min Act: -0.1700

Data Index: 4269550 (Open Web Text)

Max Activating Token Index: 156

Text #2

Max Range: 3.4785. Min Range: -3.4785

Max Act: 3.3186. Min Act: -0.1700

Data Index: 2707691 (Open Web Text)

Max Activating Token Index: 698

Text #3

Max Range: 3.4785. Min Range: -3.4785

Max Act: 3.2547. Min Act: -0.1700

Data Index: 771234 (Open Web Text)

Max Activating Token Index: 851

Text #4

Max Range: 3.4785. Min Range: -3.4785

Max Act: 3.2800. Min Act: -0.1700

Data Index: 7532165 (Open Web Text)

Max Activating Token Index: 520

Text #5

Max Range: 3.4785. Min Range: -3.4785

Max Act: 3.2726. Min Act: -0.1700

Data Index: 7910774 (Open Web Text)

Max Activating Token Index: 239

Text #6

Max Range: 3.4785. Min Range: -3.4785

Max Act: 3.2490. Min Act: -0.1700

Data Index: 1707741 (Open Web Text)

Max Activating Token Index: 270

Text #7

Max Range: 3.4785. Min Range: -3.4785

Max Act: 3.2398. Min Act: -0.1700

Data Index: 5202783 (Open Web Text)

Max Activating Token Index: 753

Text #8

Max Range: 3.4785. Min Range: -3.4785

Max Act: 3.2134. Min Act: -0.1700

Data Index: 3706082 (Open Web Text)

Max Activating Token Index: 714

Text #9

Max Range: 3.4785. Min Range: -3.4785

Max Act: 3.2363. Min Act: -0.1700

Data Index: 1720061 (Open Web Text)

Max Activating Token Index: 604

Text #10

Max Range: 3.4785. Min Range: -3.4785

Max Act: 3.2227. Min Act: -0.1700

Data Index: 3079038 (Open Web Text)

Max Activating Token Index: 865

Text #11

Max Range: 3.4785. Min Range: -3.4785

Max Act: 3.2005. Min Act: -0.1700

Data Index: 1970368 (Open Web Text)

Max Activating Token Index: 855

Text #12

Max Range: 3.4785. Min Range: -3.4785

Max Act: 3.2154. Min Act: -0.1700

Data Index: 2606298 (Open Web Text)

Max Activating Token Index: 787

Text #13

Max Range: 3.4785. Min Range: -3.4785

Max Act: 3.2005. Min Act: -0.1700

Data Index: 3454807 (Open Web Text)

Max Activating Token Index: 969

Text #14

Max Range: 3.4785. Min Range: -3.4785

Max Act: 3.2021. Min Act: -0.1700

Data Index: 3464721 (Open Web Text)

Max Activating Token Index: 681

Text #15

Max Range: 3.4785. Min Range: -3.4785

Max Act: 3.1874. Min Act: -0.1700

Data Index: 7987642 (Open Web Text)

Max Activating Token Index: 888

Text #16

Max Range: 3.4785. Min Range: -3.4785

Max Act: 3.1869. Min Act: -0.1700

Data Index: 927608 (Open Web Text)

Max Activating Token Index: 393

Text #17

Max Range: 3.4785. Min Range: -3.4785

Max Act: 3.2190. Min Act: -0.1700

Data Index: 3383698 (Open Web Text)

Max Activating Token Index: 788

Text #18

Max Range: 3.4785. Min Range: -3.4785

Max Act: 3.1601. Min Act: -0.1700

Data Index: 3493785 (Open Web Text)

Max Activating Token Index: 406

Text #19

Max Range: 3.4785. Min Range: -3.4785

Max Act: 3.1795. Min Act: -0.1700

Data Index: 1860348 (Open Web Text)

Max Activating Token Index: 489