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

Dataset: Open Web Text

Neuron 1107 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: 3.3426. Min Range: -3.3426

Max Act: 3.3426. Min Act: -0.1700

Data Index: 5571693 (Open Web Text)

Max Activating Token Index: 8

Text #1

Max Range: 3.3426. Min Range: -3.3426

Max Act: 3.3215. Min Act: -0.1700

Data Index: 794048 (Open Web Text)

Max Activating Token Index: 5

Text #2

Max Range: 3.3426. Min Range: -3.3426

Max Act: 3.2483. Min Act: -0.1700

Data Index: 8720449 (Open Web Text)

Max Activating Token Index: 4

Text #3

Max Range: 3.3426. Min Range: -3.3426

Max Act: 3.1997. Min Act: -0.1700

Data Index: 3100042 (Open Web Text)

Max Activating Token Index: 939

Text #4

Max Range: 3.3426. Min Range: -3.3426

Max Act: 3.2037. Min Act: -0.1700

Data Index: 6577117 (Open Web Text)

Max Activating Token Index: 8

Text #5

Max Range: 3.3426. Min Range: -3.3426

Max Act: 3.1535. Min Act: -0.1700

Data Index: 5649988 (Open Web Text)

Max Activating Token Index: 250

Text #6

Max Range: 3.3426. Min Range: -3.3426

Max Act: 3.1761. Min Act: -0.1700

Data Index: 5205822 (Open Web Text)

Max Activating Token Index: 1000

Text #7

Max Range: 3.3426. Min Range: -3.3426

Max Act: 3.1344. Min Act: -0.1700

Data Index: 1784886 (Open Web Text)

Max Activating Token Index: 31

Text #8

Max Range: 3.3426. Min Range: -3.3426

Max Act: 3.1242. Min Act: -0.1700

Data Index: 5248163 (Open Web Text)

Max Activating Token Index: 1002

Text #9

Max Range: 3.3426. Min Range: -3.3426

Max Act: 3.1176. Min Act: -0.1700

Data Index: 1867887 (Open Web Text)

Max Activating Token Index: 946

Text #10

Max Range: 3.3426. Min Range: -3.3426

Max Act: 3.0995. Min Act: -0.1700

Data Index: 7479888 (Open Web Text)

Max Activating Token Index: 12

Text #11

Max Range: 3.3426. Min Range: -3.3426

Max Act: 3.1012. Min Act: -0.1700

Data Index: 6675094 (Open Web Text)

Max Activating Token Index: 5

Text #12

Max Range: 3.3426. Min Range: -3.3426

Max Act: 3.0987. Min Act: -0.1700

Data Index: 3581164 (Open Web Text)

Max Activating Token Index: 74

Text #13

Max Range: 3.3426. Min Range: -3.3426

Max Act: 3.1033. Min Act: -0.1700

Data Index: 6860329 (Open Web Text)

Max Activating Token Index: 45

Text #14

Max Range: 3.3426. Min Range: -3.3426

Max Act: 3.0951. Min Act: -0.1700

Data Index: 6218337 (Open Web Text)

Max Activating Token Index: 962

Text #15

Max Range: 3.3426. Min Range: -3.3426

Max Act: 3.0842. Min Act: -0.1700

Data Index: 1855333 (Open Web Text)

Max Activating Token Index: 156

Text #16

Max Range: 3.3426. Min Range: -3.3426

Max Act: 3.0925. Min Act: -0.1700

Data Index: 1619106 (Open Web Text)

Max Activating Token Index: 842

Text #17

Max Range: 3.3426. Min Range: -3.3426

Max Act: 3.0999. Min Act: -0.1700

Data Index: 7726700 (Open Web Text)

Max Activating Token Index: 607

Text #18

Max Range: 3.3426. Min Range: -3.3426

Max Act: 3.0946. Min Act: -0.1700

Data Index: 8669468 (Open Web Text)

Max Activating Token Index: 814

Text #19

Max Range: 3.3426. Min Range: -3.3426

Max Act: 3.0991. Min Act: -0.1700

Data Index: 2874981 (Open Web Text)

Max Activating Token Index: 616