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

Dataset: Open Web Text

Neuron 131 in Layer 3

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: 4.8598. Min Range: -4.8598

Max Act: 4.8598. Min Act: -0.1700

Data Index: 6664621 (Open Web Text)

Max Activating Token Index: 358

Text #1

Max Range: 4.8598. Min Range: -4.8598

Max Act: 4.8022. Min Act: -0.1700

Data Index: 4796253 (Open Web Text)

Max Activating Token Index: 846

Text #2

Max Range: 4.8598. Min Range: -4.8598

Max Act: 4.7404. Min Act: -0.1700

Data Index: 7055310 (Open Web Text)

Max Activating Token Index: 946

Text #3

Max Range: 4.8598. Min Range: -4.8598

Max Act: 4.7311. Min Act: -0.1700

Data Index: 445479 (Open Web Text)

Max Activating Token Index: 808

Text #4

Max Range: 4.8598. Min Range: -4.8598

Max Act: 4.6730. Min Act: -0.1700

Data Index: 3887589 (Open Web Text)

Max Activating Token Index: 183

Text #5

Max Range: 4.8598. Min Range: -4.8598

Max Act: 4.7004. Min Act: -0.1700

Data Index: 4396085 (Open Web Text)

Max Activating Token Index: 239

Text #6

Max Range: 4.8598. Min Range: -4.8598

Max Act: 4.7079. Min Act: -0.1700

Data Index: 6166886 (Open Web Text)

Max Activating Token Index: 542

Text #7

Max Range: 4.8598. Min Range: -4.8598

Max Act: 4.6208. Min Act: -0.1700

Data Index: 6762877 (Open Web Text)

Max Activating Token Index: 911

Text #8

Max Range: 4.8598. Min Range: -4.8598

Max Act: 4.6609. Min Act: -0.1700

Data Index: 7238466 (Open Web Text)

Max Activating Token Index: 137

Text #9

Max Range: 4.8598. Min Range: -4.8598

Max Act: 4.6603. Min Act: -0.1700

Data Index: 1036245 (Open Web Text)

Max Activating Token Index: 729

Text #10

Max Range: 4.8598. Min Range: -4.8598

Max Act: 4.6466. Min Act: -0.1700

Data Index: 8373506 (Open Web Text)

Max Activating Token Index: 52

Text #11

Max Range: 4.8598. Min Range: -4.8598

Max Act: 4.6101. Min Act: -0.1700

Data Index: 3065454 (Open Web Text)

Max Activating Token Index: 143

Text #12

Max Range: 4.8598. Min Range: -4.8598

Max Act: 4.5904. Min Act: -0.1700

Data Index: 2676077 (Open Web Text)

Max Activating Token Index: 510

Text #13

Max Range: 4.8598. Min Range: -4.8598

Max Act: 4.6007. Min Act: -0.1700

Data Index: 7535915 (Open Web Text)

Max Activating Token Index: 926

Text #14

Max Range: 4.8598. Min Range: -4.8598

Max Act: 4.6046. Min Act: -0.1700

Data Index: 3518502 (Open Web Text)

Max Activating Token Index: 651

Text #15

Max Range: 4.8598. Min Range: -4.8598

Max Act: 4.6250. Min Act: -0.1700

Data Index: 1889019 (Open Web Text)

Max Activating Token Index: 350

Text #16

Max Range: 4.8598. Min Range: -4.8598

Max Act: 4.6024. Min Act: -0.1700

Data Index: 4662519 (Open Web Text)

Max Activating Token Index: 397

Text #17

Max Range: 4.8598. Min Range: -4.8598

Max Act: 4.5973. Min Act: -0.1700

Data Index: 1308716 (Open Web Text)

Max Activating Token Index: 724

Text #18

Max Range: 4.8598. Min Range: -4.8598

Max Act: 4.5595. Min Act: -0.1700

Data Index: 7756343 (Open Web Text)

Max Activating Token Index: 244

Text #19

Max Range: 4.8598. Min Range: -4.8598

Max Act: 4.6004. Min Act: -0.1700

Data Index: 1871277 (Open Web Text)

Max Activating Token Index: 796