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

Dataset: Open Web Text

Neuron 2559 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: 3.6094. Min Range: -3.6094

Max Act: 3.6094. Min Act: -0.1700

Data Index: 6864813 (Open Web Text)

Max Activating Token Index: 823

Text #1

Max Range: 3.6094. Min Range: -3.6094

Max Act: 3.5449. Min Act: -0.1700

Data Index: 7526710 (Open Web Text)

Max Activating Token Index: 668

Text #2

Max Range: 3.6094. Min Range: -3.6094

Max Act: 3.4276. Min Act: -0.1700

Data Index: 5776587 (Open Web Text)

Max Activating Token Index: 434

Text #3

Max Range: 3.6094. Min Range: -3.6094

Max Act: 3.4012. Min Act: -0.1700

Data Index: 617591 (Open Web Text)

Max Activating Token Index: 31

Text #4

Max Range: 3.6094. Min Range: -3.6094

Max Act: 3.4033. Min Act: -0.1700

Data Index: 481998 (Open Web Text)

Max Activating Token Index: 677

Text #5

Max Range: 3.6094. Min Range: -3.6094

Max Act: 3.3458. Min Act: -0.1700

Data Index: 5736113 (Open Web Text)

Max Activating Token Index: 981

Text #6

Max Range: 3.6094. Min Range: -3.6094

Max Act: 3.3306. Min Act: -0.1700

Data Index: 140191 (Open Web Text)

Max Activating Token Index: 634

Text #7

Max Range: 3.6094. Min Range: -3.6094

Max Act: 3.3550. Min Act: -0.1700

Data Index: 726427 (Open Web Text)

Max Activating Token Index: 5

Text #8

Max Range: 3.6094. Min Range: -3.6094

Max Act: 3.3210. Min Act: -0.1700

Data Index: 4309270 (Open Web Text)

Max Activating Token Index: 4

Text #9

Max Range: 3.6094. Min Range: -3.6094

Max Act: 3.3215. Min Act: -0.1700

Data Index: 5763626 (Open Web Text)

Max Activating Token Index: 968

Text #10

Max Range: 3.6094. Min Range: -3.6094

Max Act: 3.3199. Min Act: -0.1700

Data Index: 6171310 (Open Web Text)

Max Activating Token Index: 112

Text #11

Max Range: 3.6094. Min Range: -3.6094

Max Act: 3.3105. Min Act: -0.1700

Data Index: 1685242 (Open Web Text)

Max Activating Token Index: 841

Text #12

Max Range: 3.6094. Min Range: -3.6094

Max Act: 3.2898. Min Act: -0.1700

Data Index: 64029 (Open Web Text)

Max Activating Token Index: 546

Text #13

Max Range: 3.6094. Min Range: -3.6094

Max Act: 3.2824. Min Act: -0.1700

Data Index: 2619624 (Open Web Text)

Max Activating Token Index: 739

Text #14

Max Range: 3.6094. Min Range: -3.6094

Max Act: 3.2812. Min Act: -0.1700

Data Index: 7973441 (Open Web Text)

Max Activating Token Index: 829

Text #15

Max Range: 3.6094. Min Range: -3.6094

Max Act: 3.3060. Min Act: -0.1700

Data Index: 3588978 (Open Web Text)

Max Activating Token Index: 4

Text #16

Max Range: 3.6094. Min Range: -3.6094

Max Act: 3.3021. Min Act: -0.1700

Data Index: 4729469 (Open Web Text)

Max Activating Token Index: 990

Text #17

Max Range: 3.6094. Min Range: -3.6094

Max Act: 3.2861. Min Act: -0.1700

Data Index: 7681989 (Open Web Text)

Max Activating Token Index: 504

Text #18

Max Range: 3.6094. Min Range: -3.6094

Max Act: 3.2979. Min Act: -0.1700

Data Index: 575710 (Open Web Text)

Max Activating Token Index: 932

Text #19

Max Range: 3.6094. Min Range: -3.6094

Max Act: 3.2644. Min Act: -0.1700

Data Index: 7027572 (Open Web Text)

Max Activating Token Index: 448