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

Dataset: Open Web Text

Neuron 238 in Layer 1

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: 2.0801. Min Range: -2.0801

Max Act: 2.0801. Min Act: -0.1700

Data Index: 1262944 (Open Web Text)

Max Activating Token Index: 223

Text #1

Max Range: 2.0801. Min Range: -2.0801

Max Act: 2.0564. Min Act: -0.1700

Data Index: 4477222 (Open Web Text)

Max Activating Token Index: 1014

Text #2

Max Range: 2.0801. Min Range: -2.0801

Max Act: 2.0325. Min Act: -0.1700

Data Index: 108052 (Open Web Text)

Max Activating Token Index: 761

Text #3

Max Range: 2.0801. Min Range: -2.0801

Max Act: 1.9850. Min Act: -0.1700

Data Index: 6142847 (Open Web Text)

Max Activating Token Index: 193

Text #4

Max Range: 2.0801. Min Range: -2.0801

Max Act: 1.9859. Min Act: -0.1699

Data Index: 4745582 (Open Web Text)

Max Activating Token Index: 12

Text #5

Max Range: 2.0801. Min Range: -2.0801

Max Act: 1.9871. Min Act: -0.1700

Data Index: 3373579 (Open Web Text)

Max Activating Token Index: 71

Text #6

Max Range: 2.0801. Min Range: -2.0801

Max Act: 1.9839. Min Act: -0.1700

Data Index: 7023980 (Open Web Text)

Max Activating Token Index: 15

Text #7

Max Range: 2.0801. Min Range: -2.0801

Max Act: 1.9791. Min Act: -0.1700

Data Index: 1262943 (Open Web Text)

Max Activating Token Index: 630

Text #8

Max Range: 2.0801. Min Range: -2.0801

Max Act: 1.9608. Min Act: -0.1700

Data Index: 2213729 (Open Web Text)

Max Activating Token Index: 655

Text #9

Max Range: 2.0801. Min Range: -2.0801

Max Act: 1.9761. Min Act: -0.1700

Data Index: 3014298 (Open Web Text)

Max Activating Token Index: 480

Text #10

Max Range: 2.0801. Min Range: -2.0801

Max Act: 1.9652. Min Act: -0.1700

Data Index: 5075276 (Open Web Text)

Max Activating Token Index: 45

Text #11

Max Range: 2.0801. Min Range: -2.0801

Max Act: 1.9712. Min Act: -0.1700

Data Index: 8662829 (Open Web Text)

Max Activating Token Index: 109

Text #12

Max Range: 2.0801. Min Range: -2.0801

Max Act: 1.9596. Min Act: -0.1700

Data Index: 7262841 (Open Web Text)

Max Activating Token Index: 112

Text #13

Max Range: 2.0801. Min Range: -2.0801

Max Act: 1.9675. Min Act: -0.1699

Data Index: 5095116 (Open Web Text)

Max Activating Token Index: 149

Text #14

Max Range: 2.0801. Min Range: -2.0801

Max Act: 1.9621. Min Act: -0.1693

Data Index: 6374157 (Open Web Text)

Max Activating Token Index: 908

Text #15

Max Range: 2.0801. Min Range: -2.0801

Max Act: 1.9569. Min Act: -0.1700

Data Index: 1700326 (Open Web Text)

Max Activating Token Index: 82

Text #16

Max Range: 2.0801. Min Range: -2.0801

Max Act: 1.9550. Min Act: -0.1700

Data Index: 6924014 (Open Web Text)

Max Activating Token Index: 796

Text #17

Max Range: 2.0801. Min Range: -2.0801

Max Act: 1.9598. Min Act: -0.1700

Data Index: 48884 (Open Web Text)

Max Activating Token Index: 838

Text #18

Max Range: 2.0801. Min Range: -2.0801

Max Act: 1.9563. Min Act: -0.1683

Data Index: 1438904 (Open Web Text)

Max Activating Token Index: 669

Text #19

Max Range: 2.0801. Min Range: -2.0801

Max Act: 1.9557. Min Act: -0.1700

Data Index: 1069188 (Open Web Text)

Max Activating Token Index: 78