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

Dataset: Open Web Text

Neuron 1260 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: 3.6094. Min Range: -3.6094

Max Act: 3.6094. Min Act: -0.1700

Data Index: 1030334 (Open Web Text)

Max Activating Token Index: 15

Text #1

Max Range: 3.6094. Min Range: -3.6094

Max Act: 3.5311. Min Act: -0.1700

Data Index: 1570441 (Open Web Text)

Max Activating Token Index: 3

Text #2

Max Range: 3.6094. Min Range: -3.6094

Max Act: 3.4744. Min Act: -0.1700

Data Index: 7600540 (Open Web Text)

Max Activating Token Index: 4

Text #3

Max Range: 3.6094. Min Range: -3.6094

Max Act: 3.4204. Min Act: -0.1700

Data Index: 8675781 (Open Web Text)

Max Activating Token Index: 3

Text #4

Max Range: 3.6094. Min Range: -3.6094

Max Act: 3.4236. Min Act: -0.1700

Data Index: 3722667 (Open Web Text)

Max Activating Token Index: 12

Text #5

Max Range: 3.6094. Min Range: -3.6094

Max Act: 3.4423. Min Act: -0.1700

Data Index: 6305700 (Open Web Text)

Max Activating Token Index: 4

Text #6

Max Range: 3.6094. Min Range: -3.6094

Max Act: 3.4089. Min Act: -0.1700

Data Index: 1811257 (Open Web Text)

Max Activating Token Index: 4

Text #7

Max Range: 3.6094. Min Range: -3.6094

Max Act: 3.3984. Min Act: -0.1700

Data Index: 758605 (Open Web Text)

Max Activating Token Index: 4

Text #8

Max Range: 3.6094. Min Range: -3.6094

Max Act: 3.3927. Min Act: -0.1700

Data Index: 8222872 (Open Web Text)

Max Activating Token Index: 4

Text #9

Max Range: 3.6094. Min Range: -3.6094

Max Act: 3.4141. Min Act: -0.1700

Data Index: 1905040 (Open Web Text)

Max Activating Token Index: 14

Text #10

Max Range: 3.6094. Min Range: -3.6094

Max Act: 3.4019. Min Act: -0.1700

Data Index: 8417320 (Open Web Text)

Max Activating Token Index: 2

Text #11

Max Range: 3.6094. Min Range: -3.6094

Max Act: 3.4019. Min Act: -0.1700

Data Index: 5958083 (Open Web Text)

Max Activating Token Index: 2

Text #12

Max Range: 3.6094. Min Range: -3.6094

Max Act: 3.3838. Min Act: -0.1700

Data Index: 2084245 (Open Web Text)

Max Activating Token Index: 7

Text #13

Max Range: 3.6094. Min Range: -3.6094

Max Act: 3.3853. Min Act: -0.1700

Data Index: 4864783 (Open Web Text)

Max Activating Token Index: 2

Text #14

Max Range: 3.6094. Min Range: -3.6094

Max Act: 3.3694. Min Act: -0.1700

Data Index: 8276952 (Open Web Text)

Max Activating Token Index: 34

Text #15

Max Range: 3.6094. Min Range: -3.6094

Max Act: 3.3607. Min Act: -0.1700

Data Index: 2571295 (Open Web Text)

Max Activating Token Index: 6

Text #16

Max Range: 3.6094. Min Range: -3.6094

Max Act: 3.3553. Min Act: -0.1700

Data Index: 6193916 (Open Web Text)

Max Activating Token Index: 3

Text #17

Max Range: 3.6094. Min Range: -3.6094

Max Act: 3.3580. Min Act: -0.1700

Data Index: 2973280 (Open Web Text)

Max Activating Token Index: 3

Text #18

Max Range: 3.6094. Min Range: -3.6094

Max Act: 3.3603. Min Act: -0.1700

Data Index: 989402 (Open Web Text)

Max Activating Token Index: 12

Text #19

Max Range: 3.6094. Min Range: -3.6094

Max Act: 3.3567. Min Act: -0.1700

Data Index: 8545080 (Open Web Text)

Max Activating Token Index: 5