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

Dataset: Open Web Text

Neuron 1365 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: 3.6619. Min Range: -3.6619

Max Act: 3.6619. Min Act: -0.1700

Data Index: 1575411 (Open Web Text)

Max Activating Token Index: 4

Text #1

Max Range: 3.6619. Min Range: -3.6619

Max Act: 3.5516. Min Act: -0.1700

Data Index: 4102501 (Open Web Text)

Max Activating Token Index: 4

Text #2

Max Range: 3.6619. Min Range: -3.6619

Max Act: 3.5298. Min Act: -0.1700

Data Index: 659357 (Open Web Text)

Max Activating Token Index: 18

Text #3

Max Range: 3.6619. Min Range: -3.6619

Max Act: 3.5097. Min Act: -0.1700

Data Index: 7248688 (Open Web Text)

Max Activating Token Index: 203

Text #4

Max Range: 3.6619. Min Range: -3.6619

Max Act: 3.4958. Min Act: -0.1700

Data Index: 4746904 (Open Web Text)

Max Activating Token Index: 4

Text #5

Max Range: 3.6619. Min Range: -3.6619

Max Act: 3.5082. Min Act: -0.1700

Data Index: 2858859 (Open Web Text)

Max Activating Token Index: 22

Text #6

Max Range: 3.6619. Min Range: -3.6619

Max Act: 3.4932. Min Act: -0.1700

Data Index: 3892170 (Open Web Text)

Max Activating Token Index: 973

Text #7

Max Range: 3.6619. Min Range: -3.6619

Max Act: 3.4913. Min Act: -0.1700

Data Index: 1196873 (Open Web Text)

Max Activating Token Index: 912

Text #8

Max Range: 3.6619. Min Range: -3.6619

Max Act: 3.4394. Min Act: -0.1700

Data Index: 2135892 (Open Web Text)

Max Activating Token Index: 514

Text #9

Max Range: 3.6619. Min Range: -3.6619

Max Act: 3.4400. Min Act: -0.1700

Data Index: 5567891 (Open Web Text)

Max Activating Token Index: 611

Text #10

Max Range: 3.6619. Min Range: -3.6619

Max Act: 3.4460. Min Act: -0.1700

Data Index: 3273749 (Open Web Text)

Max Activating Token Index: 6

Text #11

Max Range: 3.6619. Min Range: -3.6619

Max Act: 3.4302. Min Act: -0.1700

Data Index: 5025042 (Open Web Text)

Max Activating Token Index: 844

Text #12

Max Range: 3.6619. Min Range: -3.6619

Max Act: 3.4444. Min Act: -0.1700

Data Index: 2771421 (Open Web Text)

Max Activating Token Index: 263

Text #13

Max Range: 3.6619. Min Range: -3.6619

Max Act: 3.4346. Min Act: -0.1700

Data Index: 8452740 (Open Web Text)

Max Activating Token Index: 805

Text #14

Max Range: 3.6619. Min Range: -3.6619

Max Act: 3.4376. Min Act: -0.1700

Data Index: 4309977 (Open Web Text)

Max Activating Token Index: 876

Text #15

Max Range: 3.6619. Min Range: -3.6619

Max Act: 3.4325. Min Act: -0.1700

Data Index: 4961708 (Open Web Text)

Max Activating Token Index: 104

Text #16

Max Range: 3.6619. Min Range: -3.6619

Max Act: 3.4217. Min Act: -0.1700

Data Index: 4746895 (Open Web Text)

Max Activating Token Index: 3

Text #17

Max Range: 3.6619. Min Range: -3.6619

Max Act: 3.4212. Min Act: -0.1700

Data Index: 5050891 (Open Web Text)

Max Activating Token Index: 8

Text #18

Max Range: 3.6619. Min Range: -3.6619

Max Act: 3.3956. Min Act: -0.1700

Data Index: 5273428 (Open Web Text)

Max Activating Token Index: 6

Text #19

Max Range: 3.6619. Min Range: -3.6619

Max Act: 3.4256. Min Act: -0.1700

Data Index: 1362393 (Open Web Text)

Max Activating Token Index: 35