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

Dataset: Open Web Text

Neuron 574 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: 6.4026. Min Range: -6.4026

Max Act: 6.3962. Min Act: -0.1700

Data Index: 2597961 (Open Web Text)

Max Activating Token Index: 905

Text #1

Max Range: 6.4026. Min Range: -6.4026

Max Act: 6.3979. Min Act: -0.1700

Data Index: 8158070 (Open Web Text)

Max Activating Token Index: 661

Text #2

Max Range: 6.4026. Min Range: -6.4026

Max Act: 6.4026. Min Act: -0.1700

Data Index: 6996035 (Open Web Text)

Max Activating Token Index: 794

Text #3

Max Range: 6.4026. Min Range: -6.4026

Max Act: 6.3561. Min Act: -0.1700

Data Index: 5131446 (Open Web Text)

Max Activating Token Index: 172

Text #4

Max Range: 6.4026. Min Range: -6.4026

Max Act: 6.3257. Min Act: -0.1700

Data Index: 1662579 (Open Web Text)

Max Activating Token Index: 964

Text #5

Max Range: 6.4026. Min Range: -6.4026

Max Act: 6.3104. Min Act: -0.1700

Data Index: 2449903 (Open Web Text)

Max Activating Token Index: 41

Text #6

Max Range: 6.4026. Min Range: -6.4026

Max Act: 6.2932. Min Act: -0.1700

Data Index: 3154741 (Open Web Text)

Max Activating Token Index: 848

Text #7

Max Range: 6.4026. Min Range: -6.4026

Max Act: 6.3340. Min Act: -0.1700

Data Index: 4076822 (Open Web Text)

Max Activating Token Index: 6

Text #8

Max Range: 6.4026. Min Range: -6.4026

Max Act: 6.3250. Min Act: -0.1700

Data Index: 3615918 (Open Web Text)

Max Activating Token Index: 879

Text #9

Max Range: 6.4026. Min Range: -6.4026

Max Act: 6.3128. Min Act: -0.1700

Data Index: 691917 (Open Web Text)

Max Activating Token Index: 491

Text #10

Max Range: 6.4026. Min Range: -6.4026

Max Act: 6.2765. Min Act: -0.1700

Data Index: 3672201 (Open Web Text)

Max Activating Token Index: 670

Text #11

Max Range: 6.4026. Min Range: -6.4026

Max Act: 6.2691. Min Act: -0.1700

Data Index: 270057 (Open Web Text)

Max Activating Token Index: 1022

Text #12

Max Range: 6.4026. Min Range: -6.4026

Max Act: 6.2432. Min Act: -0.1700

Data Index: 5415908 (Open Web Text)

Max Activating Token Index: 530

Text #13

Max Range: 6.4026. Min Range: -6.4026

Max Act: 6.2697. Min Act: -0.1700

Data Index: 4202485 (Open Web Text)

Max Activating Token Index: 21

Text #14

Max Range: 6.4026. Min Range: -6.4026

Max Act: 6.2554. Min Act: -0.1700

Data Index: 782484 (Open Web Text)

Max Activating Token Index: 16

Text #15

Max Range: 6.4026. Min Range: -6.4026

Max Act: 6.2576. Min Act: -0.1700

Data Index: 3357275 (Open Web Text)

Max Activating Token Index: 48

Text #16

Max Range: 6.4026. Min Range: -6.4026

Max Act: 6.2262. Min Act: -0.1700

Data Index: 3643926 (Open Web Text)

Max Activating Token Index: 8

Text #17

Max Range: 6.4026. Min Range: -6.4026

Max Act: 6.2241. Min Act: -0.1700

Data Index: 3903688 (Open Web Text)

Max Activating Token Index: 70

Text #18

Max Range: 6.4026. Min Range: -6.4026

Max Act: 6.2188. Min Act: -0.1700

Data Index: 2663019 (Open Web Text)

Max Activating Token Index: 1006

Text #19

Max Range: 6.4026. Min Range: -6.4026

Max Act: 6.2288. Min Act: -0.1700

Data Index: 1923398 (Open Web Text)

Max Activating Token Index: 32