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

Dataset: Open Web Text

Neuron 2940 in Layer 6

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: 4.6016. Min Range: -4.6016

Max Act: 4.5990. Min Act: -0.1700

Data Index: 5845371 (Open Web Text)

Max Activating Token Index: 288

Text #1

Max Range: 4.6016. Min Range: -4.6016

Max Act: 4.6016. Min Act: -0.1700

Data Index: 2463719 (Open Web Text)

Max Activating Token Index: 101

Text #2

Max Range: 4.6016. Min Range: -4.6016

Max Act: 4.4663. Min Act: -0.1700

Data Index: 3563012 (Open Web Text)

Max Activating Token Index: 224

Text #3

Max Range: 4.6016. Min Range: -4.6016

Max Act: 4.4506. Min Act: -0.1700

Data Index: 5750247 (Open Web Text)

Max Activating Token Index: 994

Text #4

Max Range: 4.6016. Min Range: -4.6016

Max Act: 4.3284. Min Act: -0.1700

Data Index: 5518792 (Open Web Text)

Max Activating Token Index: 850

Text #5

Max Range: 4.6016. Min Range: -4.6016

Max Act: 4.3560. Min Act: -0.1700

Data Index: 1695703 (Open Web Text)

Max Activating Token Index: 604

Text #6

Max Range: 4.6016. Min Range: -4.6016

Max Act: 4.3055. Min Act: -0.1700

Data Index: 1183606 (Open Web Text)

Max Activating Token Index: 675

Text #7

Max Range: 4.6016. Min Range: -4.6016

Max Act: 4.2998. Min Act: -0.1700

Data Index: 5700908 (Open Web Text)

Max Activating Token Index: 769

Text #8

Max Range: 4.6016. Min Range: -4.6016

Max Act: 4.3086. Min Act: -0.1700

Data Index: 4431913 (Open Web Text)

Max Activating Token Index: 895

Text #9

Max Range: 4.6016. Min Range: -4.6016

Max Act: 4.2950. Min Act: -0.1700

Data Index: 7828699 (Open Web Text)

Max Activating Token Index: 912

Text #10

Max Range: 4.6016. Min Range: -4.6016

Max Act: 4.2419. Min Act: -0.1700

Data Index: 3205307 (Open Web Text)

Max Activating Token Index: 846

Text #11

Max Range: 4.6016. Min Range: -4.6016

Max Act: 4.2646. Min Act: -0.1700

Data Index: 558230 (Open Web Text)

Max Activating Token Index: 504

Text #12

Max Range: 4.6016. Min Range: -4.6016

Max Act: 4.2980. Min Act: -0.1700

Data Index: 8386154 (Open Web Text)

Max Activating Token Index: 331

Text #13

Max Range: 4.6016. Min Range: -4.6016

Max Act: 4.2694. Min Act: -0.1700

Data Index: 1841754 (Open Web Text)

Max Activating Token Index: 402

Text #14

Max Range: 4.6016. Min Range: -4.6016

Max Act: 4.2731. Min Act: -0.1700

Data Index: 2314565 (Open Web Text)

Max Activating Token Index: 138

Text #15

Max Range: 4.6016. Min Range: -4.6016

Max Act: 4.2301. Min Act: -0.1700

Data Index: 2356474 (Open Web Text)

Max Activating Token Index: 723

Text #16

Max Range: 4.6016. Min Range: -4.6016

Max Act: 4.2459. Min Act: -0.1700

Data Index: 3982535 (Open Web Text)

Max Activating Token Index: 972

Text #17

Max Range: 4.6016. Min Range: -4.6016

Max Act: 4.2879. Min Act: -0.1700

Data Index: 1404193 (Open Web Text)

Max Activating Token Index: 578

Text #18

Max Range: 4.6016. Min Range: -4.6016

Max Act: 4.2770. Min Act: -0.1700

Data Index: 770403 (Open Web Text)

Max Activating Token Index: 100

Text #19

Max Range: 4.6016. Min Range: -4.6016

Max Act: 4.2182. Min Act: -0.1700

Data Index: 4283476 (Open Web Text)

Max Activating Token Index: 493