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

Dataset: Open Web Text

Neuron 397 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: 2.5814. Min Range: -2.5814

Max Act: 2.5814. Min Act: -0.1700

Data Index: 5461058 (Open Web Text)

Max Activating Token Index: 8

Text #1

Max Range: 2.5814. Min Range: -2.5814

Max Act: 2.5558. Min Act: -0.1700

Data Index: 3881117 (Open Web Text)

Max Activating Token Index: 8

Text #2

Max Range: 2.5814. Min Range: -2.5814

Max Act: 2.5316. Min Act: -0.1700

Data Index: 43204 (Open Web Text)

Max Activating Token Index: 9

Text #3

Max Range: 2.5814. Min Range: -2.5814

Max Act: 2.4947. Min Act: -0.1700

Data Index: 854181 (Open Web Text)

Max Activating Token Index: 33

Text #4

Max Range: 2.5814. Min Range: -2.5814

Max Act: 2.4787. Min Act: -0.1700

Data Index: 2040637 (Open Web Text)

Max Activating Token Index: 11

Text #5

Max Range: 2.5814. Min Range: -2.5814

Max Act: 2.4766. Min Act: -0.1698

Data Index: 6411803 (Open Web Text)

Max Activating Token Index: 5

Text #6

Max Range: 2.5814. Min Range: -2.5814

Max Act: 2.4401. Min Act: -0.1700

Data Index: 4971003 (Open Web Text)

Max Activating Token Index: 7

Text #7

Max Range: 2.5814. Min Range: -2.5814

Max Act: 2.4539. Min Act: -0.1700

Data Index: 1817933 (Open Web Text)

Max Activating Token Index: 12

Text #8

Max Range: 2.5814. Min Range: -2.5814

Max Act: 2.4550. Min Act: -0.1700

Data Index: 3389401 (Open Web Text)

Max Activating Token Index: 6

Text #9

Max Range: 2.5814. Min Range: -2.5814

Max Act: 2.4323. Min Act: -0.1700

Data Index: 8556949 (Open Web Text)

Max Activating Token Index: 49

Text #10

Max Range: 2.5814. Min Range: -2.5814

Max Act: 2.4348. Min Act: -0.1700

Data Index: 1042934 (Open Web Text)

Max Activating Token Index: 8

Text #11

Max Range: 2.5814. Min Range: -2.5814

Max Act: 2.4363. Min Act: -0.1700

Data Index: 4126260 (Open Web Text)

Max Activating Token Index: 4

Text #12

Max Range: 2.5814. Min Range: -2.5814

Max Act: 2.4376. Min Act: -0.1700

Data Index: 4094576 (Open Web Text)

Max Activating Token Index: 6

Text #13

Max Range: 2.5814. Min Range: -2.5814

Max Act: 2.4363. Min Act: -0.1700

Data Index: 2628567 (Open Web Text)

Max Activating Token Index: 4

Text #14

Max Range: 2.5814. Min Range: -2.5814

Max Act: 2.4265. Min Act: -0.1700

Data Index: 1340976 (Open Web Text)

Max Activating Token Index: 9

Text #15

Max Range: 2.5814. Min Range: -2.5814

Max Act: 2.4237. Min Act: -0.1700

Data Index: 4595208 (Open Web Text)

Max Activating Token Index: 7

Text #16

Max Range: 2.5814. Min Range: -2.5814

Max Act: 2.4250. Min Act: -0.1700

Data Index: 6293195 (Open Web Text)

Max Activating Token Index: 7

Text #17

Max Range: 2.5814. Min Range: -2.5814

Max Act: 2.4201. Min Act: -0.1700

Data Index: 2943285 (Open Web Text)

Max Activating Token Index: 9

Text #18

Max Range: 2.5814. Min Range: -2.5814

Max Act: 2.4075. Min Act: -0.1700

Data Index: 1122636 (Open Web Text)

Max Activating Token Index: 30

Text #19

Max Range: 2.5814. Min Range: -2.5814

Max Act: 2.4040. Min Act: -0.1700

Data Index: 4160168 (Open Web Text)

Max Activating Token Index: 11