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

Dataset: Open Web Text

Neuron 603 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: 1.8660. Min Range: -1.8660

Max Act: 1.8660. Min Act: -0.1700

Data Index: 4771001 (Open Web Text)

Max Activating Token Index: 578

Text #1

Max Range: 1.8660. Min Range: -1.8660

Max Act: 1.8320. Min Act: -0.1700

Data Index: 8831871 (Open Web Text)

Max Activating Token Index: 533

Text #2

Max Range: 1.8660. Min Range: -1.8660

Max Act: 1.8386. Min Act: -0.1699

Data Index: 3823094 (Open Web Text)

Max Activating Token Index: 264

Text #3

Max Range: 1.8660. Min Range: -1.8660

Max Act: 1.8192. Min Act: -0.1700

Data Index: 8755903 (Open Web Text)

Max Activating Token Index: 646

Text #4

Max Range: 1.8660. Min Range: -1.8660

Max Act: 1.8102. Min Act: -0.1698

Data Index: 4147645 (Open Web Text)

Max Activating Token Index: 333

Text #5

Max Range: 1.8660. Min Range: -1.8660

Max Act: 1.8091. Min Act: -0.1700

Data Index: 183777 (Open Web Text)

Max Activating Token Index: 610

Text #6

Max Range: 1.8660. Min Range: -1.8660

Max Act: 1.8156. Min Act: -0.1700

Data Index: 8477083 (Open Web Text)

Max Activating Token Index: 875

Text #7

Max Range: 1.8660. Min Range: -1.8660

Max Act: 1.8056. Min Act: -0.1700

Data Index: 1779015 (Open Web Text)

Max Activating Token Index: 362

Text #8

Max Range: 1.8660. Min Range: -1.8660

Max Act: 1.7987. Min Act: -0.1700

Data Index: 6660791 (Open Web Text)

Max Activating Token Index: 454

Text #9

Max Range: 1.8660. Min Range: -1.8660

Max Act: 1.8051. Min Act: -0.1700

Data Index: 3925364 (Open Web Text)

Max Activating Token Index: 836

Text #10

Max Range: 1.8660. Min Range: -1.8660

Max Act: 1.7967. Min Act: -0.1700

Data Index: 4753928 (Open Web Text)

Max Activating Token Index: 589

Text #11

Max Range: 1.8660. Min Range: -1.8660

Max Act: 1.7901. Min Act: -0.1700

Data Index: 5962307 (Open Web Text)

Max Activating Token Index: 558

Text #12

Max Range: 1.8660. Min Range: -1.8660

Max Act: 1.7892. Min Act: -0.1700

Data Index: 7883857 (Open Web Text)

Max Activating Token Index: 197

Text #13

Max Range: 1.8660. Min Range: -1.8660

Max Act: 1.7852. Min Act: -0.1700

Data Index: 931544 (Open Web Text)

Max Activating Token Index: 690

Text #14

Max Range: 1.8660. Min Range: -1.8660

Max Act: 1.7952. Min Act: -0.1700

Data Index: 7150802 (Open Web Text)

Max Activating Token Index: 461

Text #15

Max Range: 1.8660. Min Range: -1.8660

Max Act: 1.7904. Min Act: -0.1700

Data Index: 2770856 (Open Web Text)

Max Activating Token Index: 158

Text #16

Max Range: 1.8660. Min Range: -1.8660

Max Act: 1.7914. Min Act: -0.1700

Data Index: 6508934 (Open Web Text)

Max Activating Token Index: 726

Text #17

Max Range: 1.8660. Min Range: -1.8660

Max Act: 1.7927. Min Act: -0.1700

Data Index: 8755894 (Open Web Text)

Max Activating Token Index: 250

Text #18

Max Range: 1.8660. Min Range: -1.8660

Max Act: 1.7930. Min Act: -0.1700

Data Index: 8503354 (Open Web Text)

Max Activating Token Index: 580

Text #19

Max Range: 1.8660. Min Range: -1.8660

Max Act: 1.7837. Min Act: -0.1700

Data Index: 5436884 (Open Web Text)

Max Activating Token Index: 752