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

Dataset: Open Web Text

Neuron 2230 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: 3.0338. Min Range: -3.0338

Max Act: 3.0338. Min Act: -0.1700

Data Index: 7281677 (Open Web Text)

Max Activating Token Index: 2

Text #1

Max Range: 3.0338. Min Range: -3.0338

Max Act: 3.0215. Min Act: -0.1700

Data Index: 3728541 (Open Web Text)

Max Activating Token Index: 2

Text #2

Max Range: 3.0338. Min Range: -3.0338

Max Act: 3.0052. Min Act: -0.1700

Data Index: 418100 (Open Web Text)

Max Activating Token Index: 2

Text #3

Max Range: 3.0338. Min Range: -3.0338

Max Act: 2.9971. Min Act: -0.1700

Data Index: 5428040 (Open Web Text)

Max Activating Token Index: 4

Text #4

Max Range: 3.0338. Min Range: -3.0338

Max Act: 3.0031. Min Act: -0.1700

Data Index: 1446824 (Open Web Text)

Max Activating Token Index: 3

Text #5

Max Range: 3.0338. Min Range: -3.0338

Max Act: 2.9816. Min Act: -0.1700

Data Index: 5243093 (Open Web Text)

Max Activating Token Index: 5

Text #6

Max Range: 3.0338. Min Range: -3.0338

Max Act: 2.9685. Min Act: -0.1700

Data Index: 2047367 (Open Web Text)

Max Activating Token Index: 3

Text #7

Max Range: 3.0338. Min Range: -3.0338

Max Act: 2.9731. Min Act: -0.1700

Data Index: 1016436 (Open Web Text)

Max Activating Token Index: 2

Text #8

Max Range: 3.0338. Min Range: -3.0338

Max Act: 2.9471. Min Act: -0.1700

Data Index: 4083747 (Open Web Text)

Max Activating Token Index: 3

Text #9

Max Range: 3.0338. Min Range: -3.0338

Max Act: 2.9455. Min Act: -0.1700

Data Index: 4462437 (Open Web Text)

Max Activating Token Index: 3

Text #10

Max Range: 3.0338. Min Range: -3.0338

Max Act: 2.9312. Min Act: -0.1700

Data Index: 7751688 (Open Web Text)

Max Activating Token Index: 4

Text #11

Max Range: 3.0338. Min Range: -3.0338

Max Act: 2.9438. Min Act: -0.1700

Data Index: 394128 (Open Web Text)

Max Activating Token Index: 2

Text #12

Max Range: 3.0338. Min Range: -3.0338

Max Act: 2.9279. Min Act: -0.1700

Data Index: 8653853 (Open Web Text)

Max Activating Token Index: 2

Text #13

Max Range: 3.0338. Min Range: -3.0338

Max Act: 2.9258. Min Act: -0.1700

Data Index: 1648515 (Open Web Text)

Max Activating Token Index: 4

Text #14

Max Range: 3.0338. Min Range: -3.0338

Max Act: 2.9293. Min Act: -0.1700

Data Index: 2757612 (Open Web Text)

Max Activating Token Index: 2

Text #15

Max Range: 3.0338. Min Range: -3.0338

Max Act: 2.9356. Min Act: -0.1700

Data Index: 5788756 (Open Web Text)

Max Activating Token Index: 2

Text #16

Max Range: 3.0338. Min Range: -3.0338

Max Act: 2.9133. Min Act: -0.1700

Data Index: 1839589 (Open Web Text)

Max Activating Token Index: 2

Text #17

Max Range: 3.0338. Min Range: -3.0338

Max Act: 2.9133. Min Act: -0.1700

Data Index: 2283336 (Open Web Text)

Max Activating Token Index: 2

Text #18

Max Range: 3.0338. Min Range: -3.0338

Max Act: 2.9176. Min Act: -0.1700

Data Index: 5436872 (Open Web Text)

Max Activating Token Index: 1000

Text #19

Max Range: 3.0338. Min Range: -3.0338

Max Act: 2.9133. Min Act: -0.1700

Data Index: 5603982 (Open Web Text)

Max Activating Token Index: 2