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

Dataset: Open Web Text

Neuron 1991 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: 3.4614. Min Range: -3.4614

Max Act: 3.4614. Min Act: -0.1700

Data Index: 7365083 (Open Web Text)

Max Activating Token Index: 992

Text #1

Max Range: 3.4614. Min Range: -3.4614

Max Act: 3.4083. Min Act: -0.1700

Data Index: 4069827 (Open Web Text)

Max Activating Token Index: 781

Text #2

Max Range: 3.4614. Min Range: -3.4614

Max Act: 3.3855. Min Act: -0.1700

Data Index: 3263269 (Open Web Text)

Max Activating Token Index: 1008

Text #3

Max Range: 3.4614. Min Range: -3.4614

Max Act: 3.3619. Min Act: -0.1700

Data Index: 6531829 (Open Web Text)

Max Activating Token Index: 693

Text #4

Max Range: 3.4614. Min Range: -3.4614

Max Act: 3.3471. Min Act: -0.1700

Data Index: 4318938 (Open Web Text)

Max Activating Token Index: 218

Text #5

Max Range: 3.4614. Min Range: -3.4614

Max Act: 3.3399. Min Act: -0.1700

Data Index: 8229855 (Open Web Text)

Max Activating Token Index: 10

Text #6

Max Range: 3.4614. Min Range: -3.4614

Max Act: 3.3257. Min Act: -0.1700

Data Index: 6328516 (Open Web Text)

Max Activating Token Index: 9

Text #7

Max Range: 3.4614. Min Range: -3.4614

Max Act: 3.3282. Min Act: -0.1700

Data Index: 289666 (Open Web Text)

Max Activating Token Index: 556

Text #8

Max Range: 3.4614. Min Range: -3.4614

Max Act: 3.3321. Min Act: -0.1700

Data Index: 8605613 (Open Web Text)

Max Activating Token Index: 3

Text #9

Max Range: 3.4614. Min Range: -3.4614

Max Act: 3.3083. Min Act: -0.1700

Data Index: 5318853 (Open Web Text)

Max Activating Token Index: 951

Text #10

Max Range: 3.4614. Min Range: -3.4614

Max Act: 3.3022. Min Act: -0.1700

Data Index: 4062647 (Open Web Text)

Max Activating Token Index: 704

Text #11

Max Range: 3.4614. Min Range: -3.4614

Max Act: 3.3192. Min Act: -0.1700

Data Index: 2163408 (Open Web Text)

Max Activating Token Index: 285

Text #12

Max Range: 3.4614. Min Range: -3.4614

Max Act: 3.3179. Min Act: -0.1700

Data Index: 43317 (Open Web Text)

Max Activating Token Index: 255

Text #13

Max Range: 3.4614. Min Range: -3.4614

Max Act: 3.3129. Min Act: -0.1700

Data Index: 2128617 (Open Web Text)

Max Activating Token Index: 371

Text #14

Max Range: 3.4614. Min Range: -3.4614

Max Act: 3.3119. Min Act: -0.1700

Data Index: 2965254 (Open Web Text)

Max Activating Token Index: 230

Text #15

Max Range: 3.4614. Min Range: -3.4614

Max Act: 3.3126. Min Act: -0.1700

Data Index: 7264882 (Open Web Text)

Max Activating Token Index: 313

Text #16

Max Range: 3.4614. Min Range: -3.4614

Max Act: 3.2900. Min Act: -0.1700

Data Index: 579046 (Open Web Text)

Max Activating Token Index: 961

Text #17

Max Range: 3.4614. Min Range: -3.4614

Max Act: 3.2910. Min Act: -0.1700

Data Index: 4094732 (Open Web Text)

Max Activating Token Index: 974

Text #18

Max Range: 3.4614. Min Range: -3.4614

Max Act: 3.2967. Min Act: -0.1700

Data Index: 1339075 (Open Web Text)

Max Activating Token Index: 163

Text #19

Max Range: 3.4614. Min Range: -3.4614

Max Act: 3.2862. Min Act: -0.1700

Data Index: 2593864 (Open Web Text)

Max Activating Token Index: 680