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

Dataset: Open Web Text

Neuron 1456 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: 3.2213. Min Range: -3.2213

Max Act: 3.2213. Min Act: -0.1700

Data Index: 2540731 (Open Web Text)

Max Activating Token Index: 421

Text #1

Max Range: 3.2213. Min Range: -3.2213

Max Act: 3.0734. Min Act: -0.1700

Data Index: 1701658 (Open Web Text)

Max Activating Token Index: 398

Text #2

Max Range: 3.2213. Min Range: -3.2213

Max Act: 2.9739. Min Act: -0.1700

Data Index: 1525474 (Open Web Text)

Max Activating Token Index: 837

Text #3

Max Range: 3.2213. Min Range: -3.2213

Max Act: 3.0065. Min Act: -0.1700

Data Index: 7344825 (Open Web Text)

Max Activating Token Index: 683

Text #4

Max Range: 3.2213. Min Range: -3.2213

Max Act: 2.9853. Min Act: -0.1700

Data Index: 1488948 (Open Web Text)

Max Activating Token Index: 477

Text #5

Max Range: 3.2213. Min Range: -3.2213

Max Act: 2.9795. Min Act: -0.1700

Data Index: 8076354 (Open Web Text)

Max Activating Token Index: 567

Text #6

Max Range: 3.2213. Min Range: -3.2213

Max Act: 2.9998. Min Act: -0.1700

Data Index: 5032667 (Open Web Text)

Max Activating Token Index: 84

Text #7

Max Range: 3.2213. Min Range: -3.2213

Max Act: 2.9389. Min Act: -0.1700

Data Index: 806223 (Open Web Text)

Max Activating Token Index: 261

Text #8

Max Range: 3.2213. Min Range: -3.2213

Max Act: 2.9497. Min Act: -0.1700

Data Index: 1578293 (Open Web Text)

Max Activating Token Index: 428

Text #9

Max Range: 3.2213. Min Range: -3.2213

Max Act: 2.9687. Min Act: -0.1700

Data Index: 2681182 (Open Web Text)

Max Activating Token Index: 980

Text #10

Max Range: 3.2213. Min Range: -3.2213

Max Act: 2.9384. Min Act: -0.1700

Data Index: 3093360 (Open Web Text)

Max Activating Token Index: 979

Text #11

Max Range: 3.2213. Min Range: -3.2213

Max Act: 2.9057. Min Act: -0.1700

Data Index: 2547034 (Open Web Text)

Max Activating Token Index: 271

Text #12

Max Range: 3.2213. Min Range: -3.2213

Max Act: 2.9107. Min Act: -0.1700

Data Index: 2026875 (Open Web Text)

Max Activating Token Index: 711

Text #13

Max Range: 3.2213. Min Range: -3.2213

Max Act: 2.9125. Min Act: -0.1700

Data Index: 3997314 (Open Web Text)

Max Activating Token Index: 280

Text #14

Max Range: 3.2213. Min Range: -3.2213

Max Act: 2.9080. Min Act: -0.1700

Data Index: 8727529 (Open Web Text)

Max Activating Token Index: 326

Text #15

Max Range: 3.2213. Min Range: -3.2213

Max Act: 2.8777. Min Act: -0.1700

Data Index: 5669650 (Open Web Text)

Max Activating Token Index: 489

Text #16

Max Range: 3.2213. Min Range: -3.2213

Max Act: 2.8956. Min Act: -0.1700

Data Index: 7896599 (Open Web Text)

Max Activating Token Index: 454

Text #17

Max Range: 3.2213. Min Range: -3.2213

Max Act: 2.8816. Min Act: -0.1700

Data Index: 7888401 (Open Web Text)

Max Activating Token Index: 488

Text #18

Max Range: 3.2213. Min Range: -3.2213

Max Act: 2.8905. Min Act: -0.1700

Data Index: 2647153 (Open Web Text)

Max Activating Token Index: 887

Text #19

Max Range: 3.2213. Min Range: -3.2213

Max Act: 2.8793. Min Act: -0.1700

Data Index: 5357138 (Open Web Text)

Max Activating Token Index: 735