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

Dataset: Open Web Text

Neuron 2910 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: 5.1027. Min Range: -5.1027

Max Act: 5.1027. Min Act: -0.1700

Data Index: 5133446 (Open Web Text)

Max Activating Token Index: 495

Text #1

Max Range: 5.1027. Min Range: -5.1027

Max Act: 5.0368. Min Act: -0.1700

Data Index: 6833296 (Open Web Text)

Max Activating Token Index: 348

Text #2

Max Range: 5.1027. Min Range: -5.1027

Max Act: 5.0311. Min Act: -0.1700

Data Index: 3906948 (Open Web Text)

Max Activating Token Index: 12

Text #3

Max Range: 5.1027. Min Range: -5.1027

Max Act: 4.9794. Min Act: -0.1700

Data Index: 338527 (Open Web Text)

Max Activating Token Index: 390

Text #4

Max Range: 5.1027. Min Range: -5.1027

Max Act: 4.9713. Min Act: -0.1700

Data Index: 8285024 (Open Web Text)

Max Activating Token Index: 569

Text #5

Max Range: 5.1027. Min Range: -5.1027

Max Act: 4.9745. Min Act: -0.1700

Data Index: 3777559 (Open Web Text)

Max Activating Token Index: 881

Text #6

Max Range: 5.1027. Min Range: -5.1027

Max Act: 4.9726. Min Act: -0.1700

Data Index: 3076982 (Open Web Text)

Max Activating Token Index: 284

Text #7

Max Range: 5.1027. Min Range: -5.1027

Max Act: 4.9584. Min Act: -0.1700

Data Index: 1018100 (Open Web Text)

Max Activating Token Index: 135

Text #8

Max Range: 5.1027. Min Range: -5.1027

Max Act: 4.9766. Min Act: -0.1700

Data Index: 8180478 (Open Web Text)

Max Activating Token Index: 270

Text #9

Max Range: 5.1027. Min Range: -5.1027

Max Act: 4.9584. Min Act: -0.1700

Data Index: 4053408 (Open Web Text)

Max Activating Token Index: 795

Text #10

Max Range: 5.1027. Min Range: -5.1027

Max Act: 4.9850. Min Act: -0.1700

Data Index: 978066 (Open Web Text)

Max Activating Token Index: 620

Text #11

Max Range: 5.1027. Min Range: -5.1027

Max Act: 4.9228. Min Act: -0.1700

Data Index: 4273390 (Open Web Text)

Max Activating Token Index: 993

Text #12

Max Range: 5.1027. Min Range: -5.1027

Max Act: 4.9262. Min Act: -0.1700

Data Index: 6976121 (Open Web Text)

Max Activating Token Index: 938

Text #13

Max Range: 5.1027. Min Range: -5.1027

Max Act: 4.9021. Min Act: -0.1700

Data Index: 7262169 (Open Web Text)

Max Activating Token Index: 893

Text #14

Max Range: 5.1027. Min Range: -5.1027

Max Act: 4.9151. Min Act: -0.1700

Data Index: 2336264 (Open Web Text)

Max Activating Token Index: 220

Text #15

Max Range: 5.1027. Min Range: -5.1027

Max Act: 4.9260. Min Act: -0.1700

Data Index: 3441960 (Open Web Text)

Max Activating Token Index: 423

Text #16

Max Range: 5.1027. Min Range: -5.1027

Max Act: 4.9493. Min Act: -0.1700

Data Index: 4853435 (Open Web Text)

Max Activating Token Index: 67

Text #17

Max Range: 5.1027. Min Range: -5.1027

Max Act: 4.9337. Min Act: -0.1700

Data Index: 6477196 (Open Web Text)

Max Activating Token Index: 472

Text #18

Max Range: 5.1027. Min Range: -5.1027

Max Act: 4.9003. Min Act: -0.1700

Data Index: 1699988 (Open Web Text)

Max Activating Token Index: 195

Text #19

Max Range: 5.1027. Min Range: -5.1027

Max Act: 4.9058. Min Act: -0.1700

Data Index: 1454198 (Open Web Text)

Max Activating Token Index: 853