Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer

Dataset: Open Web Text

Neuron 1665 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')

Text #0

Max Range: 5.8080. Min Range: -5.8080

Max Act: 5.8080. Min Act: -0.1700

Data Index: 2888311 (Open Web Text)

Max Activating Token Index: 114

Text #1

Max Range: 5.8080. Min Range: -5.8080

Max Act: 5.7143. Min Act: -0.1700

Data Index: 5593567 (Open Web Text)

Max Activating Token Index: 423

Text #2

Max Range: 5.8080. Min Range: -5.8080

Max Act: 5.6518. Min Act: -0.1700

Data Index: 4749326 (Open Web Text)

Max Activating Token Index: 246

Text #3

Max Range: 5.8080. Min Range: -5.8080

Max Act: 5.5893. Min Act: -0.1700

Data Index: 7789577 (Open Web Text)

Max Activating Token Index: 545

Text #4

Max Range: 5.8080. Min Range: -5.8080

Max Act: 5.6205. Min Act: -0.1700

Data Index: 2570477 (Open Web Text)

Max Activating Token Index: 706

Text #5

Max Range: 5.8080. Min Range: -5.8080

Max Act: 5.6830. Min Act: -0.1700

Data Index: 946581 (Open Web Text)

Max Activating Token Index: 279

Text #6

Max Range: 5.8080. Min Range: -5.8080

Max Act: 5.6518. Min Act: -0.1700

Data Index: 1353190 (Open Web Text)

Max Activating Token Index: 5

Text #7

Max Range: 5.8080. Min Range: -5.8080

Max Act: 5.5580. Min Act: -0.1700

Data Index: 1045682 (Open Web Text)

Max Activating Token Index: 337

Text #8

Max Range: 5.8080. Min Range: -5.8080

Max Act: 5.6518. Min Act: -0.1700

Data Index: 5075380 (Open Web Text)

Max Activating Token Index: 921

Text #9

Max Range: 5.8080. Min Range: -5.8080

Max Act: 5.6205. Min Act: -0.1700

Data Index: 830689 (Open Web Text)

Max Activating Token Index: 964

Text #10

Max Range: 5.8080. Min Range: -5.8080

Max Act: 5.5893. Min Act: -0.1700

Data Index: 7571955 (Open Web Text)

Max Activating Token Index: 918

Text #11

Max Range: 5.8080. Min Range: -5.8080

Max Act: 5.5893. Min Act: -0.1700

Data Index: 5064398 (Open Web Text)

Max Activating Token Index: 7

Text #12

Max Range: 5.8080. Min Range: -5.8080

Max Act: 5.5580. Min Act: -0.1700

Data Index: 8296126 (Open Web Text)

Max Activating Token Index: 610

Text #13

Max Range: 5.8080. Min Range: -5.8080

Max Act: 5.6205. Min Act: -0.1700

Data Index: 7222165 (Open Web Text)

Max Activating Token Index: 384

Text #14

Max Range: 5.8080. Min Range: -5.8080

Max Act: 5.6205. Min Act: -0.1700

Data Index: 5804640 (Open Web Text)

Max Activating Token Index: 71

Text #15

Max Range: 5.8080. Min Range: -5.8080

Max Act: 5.6205. Min Act: -0.1700

Data Index: 8125015 (Open Web Text)

Max Activating Token Index: 573

Text #16

Max Range: 5.8080. Min Range: -5.8080

Max Act: 5.5580. Min Act: -0.1700

Data Index: 7545015 (Open Web Text)

Max Activating Token Index: 46

Text #17

Max Range: 5.8080. Min Range: -5.8080

Max Act: 5.5268. Min Act: -0.1700

Data Index: 2365178 (Open Web Text)

Max Activating Token Index: 434

Text #18

Max Range: 5.8080. Min Range: -5.8080

Max Act: 5.5268. Min Act: -0.1700

Data Index: 3525754 (Open Web Text)

Max Activating Token Index: 372

Text #19

Max Range: 5.8080. Min Range: -5.8080

Max Act: 5.5268. Min Act: -0.1700

Data Index: 122417 (Open Web Text)

Max Activating Token Index: 89