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

Dataset: Open Web Text

Neuron 401 in Layer 6

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: 4.1850. Min Range: -4.1850

Max Act: 4.1850. Min Act: -0.1700

Data Index: 1484057 (Open Web Text)

Max Activating Token Index: 778

Text #1

Max Range: 4.1850. Min Range: -4.1850

Max Act: 4.1084. Min Act: -0.1700

Data Index: 7300399 (Open Web Text)

Max Activating Token Index: 1010

Text #2

Max Range: 4.1850. Min Range: -4.1850

Max Act: 4.1271. Min Act: -0.1700

Data Index: 6016770 (Open Web Text)

Max Activating Token Index: 408

Text #3

Max Range: 4.1850. Min Range: -4.1850

Max Act: 4.1248. Min Act: -0.1700

Data Index: 281245 (Open Web Text)

Max Activating Token Index: 550

Text #4

Max Range: 4.1850. Min Range: -4.1850

Max Act: 4.0594. Min Act: -0.1700

Data Index: 1757728 (Open Web Text)

Max Activating Token Index: 66

Text #5

Max Range: 4.1850. Min Range: -4.1850

Max Act: 4.0729. Min Act: -0.1700

Data Index: 7809904 (Open Web Text)

Max Activating Token Index: 539

Text #6

Max Range: 4.1850. Min Range: -4.1850

Max Act: 4.0924. Min Act: -0.1700

Data Index: 4349069 (Open Web Text)

Max Activating Token Index: 773

Text #7

Max Range: 4.1850. Min Range: -4.1850

Max Act: 4.0783. Min Act: -0.1700

Data Index: 2037326 (Open Web Text)

Max Activating Token Index: 131

Text #8

Max Range: 4.1850. Min Range: -4.1850

Max Act: 4.0724. Min Act: -0.1700

Data Index: 7314536 (Open Web Text)

Max Activating Token Index: 255

Text #9

Max Range: 4.1850. Min Range: -4.1850

Max Act: 4.0837. Min Act: -0.1700

Data Index: 6521430 (Open Web Text)

Max Activating Token Index: 54

Text #10

Max Range: 4.1850. Min Range: -4.1850

Max Act: 4.0610. Min Act: -0.1700

Data Index: 5749103 (Open Web Text)

Max Activating Token Index: 778

Text #11

Max Range: 4.1850. Min Range: -4.1850

Max Act: 4.0919. Min Act: -0.1700

Data Index: 8330856 (Open Web Text)

Max Activating Token Index: 560

Text #12

Max Range: 4.1850. Min Range: -4.1850

Max Act: 4.0308. Min Act: -0.1700

Data Index: 3852037 (Open Web Text)

Max Activating Token Index: 482

Text #13

Max Range: 4.1850. Min Range: -4.1850

Max Act: 4.0523. Min Act: -0.1700

Data Index: 5456903 (Open Web Text)

Max Activating Token Index: 413

Text #14

Max Range: 4.1850. Min Range: -4.1850

Max Act: 4.0327. Min Act: -0.1700

Data Index: 5430285 (Open Web Text)

Max Activating Token Index: 410

Text #15

Max Range: 4.1850. Min Range: -4.1850

Max Act: 4.0509. Min Act: -0.1700

Data Index: 7807816 (Open Web Text)

Max Activating Token Index: 959

Text #16

Max Range: 4.1850. Min Range: -4.1850

Max Act: 4.0452. Min Act: -0.1700

Data Index: 4296261 (Open Web Text)

Max Activating Token Index: 372

Text #17

Max Range: 4.1850. Min Range: -4.1850

Max Act: 4.0509. Min Act: -0.1700

Data Index: 3443840 (Open Web Text)

Max Activating Token Index: 18

Text #18

Max Range: 4.1850. Min Range: -4.1850

Max Act: 4.0639. Min Act: -0.1700

Data Index: 5035067 (Open Web Text)

Max Activating Token Index: 579

Text #19

Max Range: 4.1850. Min Range: -4.1850

Max Act: 4.0521. Min Act: -0.1700

Data Index: 4436732 (Open Web Text)

Max Activating Token Index: 887