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

Dataset: Open Web Text

Neuron 1558 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: 4.8333. Min Range: -4.8333

Max Act: 4.8333. Min Act: -0.1700

Data Index: 2476023 (Open Web Text)

Max Activating Token Index: 15

Text #1

Max Range: 4.8333. Min Range: -4.8333

Max Act: 4.7417. Min Act: -0.1700

Data Index: 1841880 (Open Web Text)

Max Activating Token Index: 12

Text #2

Max Range: 4.8333. Min Range: -4.8333

Max Act: 4.7554. Min Act: -0.1700

Data Index: 8050716 (Open Web Text)

Max Activating Token Index: 10

Text #3

Max Range: 4.8333. Min Range: -4.8333

Max Act: 4.7143. Min Act: -0.1700

Data Index: 8155343 (Open Web Text)

Max Activating Token Index: 8

Text #4

Max Range: 4.8333. Min Range: -4.8333

Max Act: 4.7094. Min Act: -0.1700

Data Index: 2774776 (Open Web Text)

Max Activating Token Index: 19

Text #5

Max Range: 4.8333. Min Range: -4.8333

Max Act: 4.6845. Min Act: -0.1700

Data Index: 7349556 (Open Web Text)

Max Activating Token Index: 15

Text #6

Max Range: 4.8333. Min Range: -4.8333

Max Act: 4.6754. Min Act: -0.1700

Data Index: 7494365 (Open Web Text)

Max Activating Token Index: 8

Text #7

Max Range: 4.8333. Min Range: -4.8333

Max Act: 4.6919. Min Act: -0.1700

Data Index: 731475 (Open Web Text)

Max Activating Token Index: 7

Text #8

Max Range: 4.8333. Min Range: -4.8333

Max Act: 4.6849. Min Act: -0.1700

Data Index: 2146522 (Open Web Text)

Max Activating Token Index: 21

Text #9

Max Range: 4.8333. Min Range: -4.8333

Max Act: 4.7004. Min Act: -0.1700

Data Index: 2277328 (Open Web Text)

Max Activating Token Index: 10

Text #10

Max Range: 4.8333. Min Range: -4.8333

Max Act: 4.6928. Min Act: -0.1700

Data Index: 7135759 (Open Web Text)

Max Activating Token Index: 11

Text #11

Max Range: 4.8333. Min Range: -4.8333

Max Act: 4.6702. Min Act: -0.1700

Data Index: 2291918 (Open Web Text)

Max Activating Token Index: 19

Text #12

Max Range: 4.8333. Min Range: -4.8333

Max Act: 4.6704. Min Act: -0.1700

Data Index: 7134541 (Open Web Text)

Max Activating Token Index: 15

Text #13

Max Range: 4.8333. Min Range: -4.8333

Max Act: 4.6647. Min Act: -0.1700

Data Index: 1982757 (Open Web Text)

Max Activating Token Index: 18

Text #14

Max Range: 4.8333. Min Range: -4.8333

Max Act: 4.6721. Min Act: -0.1700

Data Index: 935490 (Open Web Text)

Max Activating Token Index: 9

Text #15

Max Range: 4.8333. Min Range: -4.8333

Max Act: 4.6704. Min Act: -0.1700

Data Index: 7952735 (Open Web Text)

Max Activating Token Index: 5

Text #16

Max Range: 4.8333. Min Range: -4.8333

Max Act: 4.6267. Min Act: -0.1700

Data Index: 6759329 (Open Web Text)

Max Activating Token Index: 26

Text #17

Max Range: 4.8333. Min Range: -4.8333

Max Act: 4.6176. Min Act: -0.1700

Data Index: 6913504 (Open Web Text)

Max Activating Token Index: 15

Text #18

Max Range: 4.8333. Min Range: -4.8333

Max Act: 4.6281. Min Act: -0.1700

Data Index: 6954323 (Open Web Text)

Max Activating Token Index: 42

Text #19

Max Range: 4.8333. Min Range: -4.8333

Max Act: 4.6409. Min Act: -0.1700

Data Index: 485301 (Open Web Text)

Max Activating Token Index: 5