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

Dataset: Open Web Text

Neuron 1891 in Layer 1

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: 4.6116. Min Range: -4.6116

Max Act: 4.6116. Min Act: -0.1700

Data Index: 5054309 (Open Web Text)

Max Activating Token Index: 535

Text #1

Max Range: 4.6116. Min Range: -4.6116

Max Act: 4.6019. Min Act: -0.1700

Data Index: 3701660 (Open Web Text)

Max Activating Token Index: 524

Text #2

Max Range: 4.6116. Min Range: -4.6116

Max Act: 4.5981. Min Act: -0.1700

Data Index: 1106100 (Open Web Text)

Max Activating Token Index: 18

Text #3

Max Range: 4.6116. Min Range: -4.6116

Max Act: 4.5086. Min Act: -0.1700

Data Index: 5587964 (Open Web Text)

Max Activating Token Index: 306

Text #4

Max Range: 4.6116. Min Range: -4.6116

Max Act: 4.5216. Min Act: -0.1700

Data Index: 6447623 (Open Web Text)

Max Activating Token Index: 354

Text #5

Max Range: 4.6116. Min Range: -4.6116

Max Act: 4.5320. Min Act: -0.1700

Data Index: 3054698 (Open Web Text)

Max Activating Token Index: 609

Text #6

Max Range: 4.6116. Min Range: -4.6116

Max Act: 4.5411. Min Act: -0.1700

Data Index: 8653932 (Open Web Text)

Max Activating Token Index: 228

Text #7

Max Range: 4.6116. Min Range: -4.6116

Max Act: 4.4928. Min Act: -0.1700

Data Index: 5507333 (Open Web Text)

Max Activating Token Index: 752

Text #8

Max Range: 4.6116. Min Range: -4.6116

Max Act: 4.5071. Min Act: -0.1700

Data Index: 4865703 (Open Web Text)

Max Activating Token Index: 366

Text #9

Max Range: 4.6116. Min Range: -4.6116

Max Act: 4.4982. Min Act: -0.1700

Data Index: 6525131 (Open Web Text)

Max Activating Token Index: 167

Text #10

Max Range: 4.6116. Min Range: -4.6116

Max Act: 4.4708. Min Act: -0.1700

Data Index: 176005 (Open Web Text)

Max Activating Token Index: 15

Text #11

Max Range: 4.6116. Min Range: -4.6116

Max Act: 4.4707. Min Act: -0.1700

Data Index: 3739166 (Open Web Text)

Max Activating Token Index: 490

Text #12

Max Range: 4.6116. Min Range: -4.6116

Max Act: 4.4457. Min Act: -0.1700

Data Index: 3867708 (Open Web Text)

Max Activating Token Index: 82

Text #13

Max Range: 4.6116. Min Range: -4.6116

Max Act: 4.4554. Min Act: -0.1700

Data Index: 4012872 (Open Web Text)

Max Activating Token Index: 171

Text #14

Max Range: 4.6116. Min Range: -4.6116

Max Act: 4.4683. Min Act: -0.1700

Data Index: 4054255 (Open Web Text)

Max Activating Token Index: 126

Text #15

Max Range: 4.6116. Min Range: -4.6116

Max Act: 4.4575. Min Act: -0.1700

Data Index: 4239523 (Open Web Text)

Max Activating Token Index: 542

Text #16

Max Range: 4.6116. Min Range: -4.6116

Max Act: 4.4627. Min Act: -0.1700

Data Index: 1730231 (Open Web Text)

Max Activating Token Index: 480

Text #17

Max Range: 4.6116. Min Range: -4.6116

Max Act: 4.4609. Min Act: -0.1700

Data Index: 4430315 (Open Web Text)

Max Activating Token Index: 485

Text #18

Max Range: 4.6116. Min Range: -4.6116

Max Act: 4.4512. Min Act: -0.1700

Data Index: 4761265 (Open Web Text)

Max Activating Token Index: 252

Text #19

Max Range: 4.6116. Min Range: -4.6116

Max Act: 4.4772. Min Act: -0.1700

Data Index: 2486242 (Open Web Text)

Max Activating Token Index: 82