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

Dataset: Open Web Text

Neuron 983 in Layer 2

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: 5.0542. Min Range: -5.0542

Max Act: 5.0542. Min Act: -0.1699

Data Index: 956581 (Open Web Text)

Max Activating Token Index: 638

Text #1

Max Range: 5.0542. Min Range: -5.0542

Max Act: 4.9691. Min Act: -0.1700

Data Index: 8813062 (Open Web Text)

Max Activating Token Index: 807

Text #2

Max Range: 5.0542. Min Range: -5.0542

Max Act: 5.0171. Min Act: -0.1700

Data Index: 5392524 (Open Web Text)

Max Activating Token Index: 494

Text #3

Max Range: 5.0542. Min Range: -5.0542

Max Act: 4.9832. Min Act: -0.1700

Data Index: 1739053 (Open Web Text)

Max Activating Token Index: 71

Text #4

Max Range: 5.0542. Min Range: -5.0542

Max Act: 4.9970. Min Act: -0.1699

Data Index: 6041474 (Open Web Text)

Max Activating Token Index: 780

Text #5

Max Range: 5.0542. Min Range: -5.0542

Max Act: 4.9892. Min Act: -0.1700

Data Index: 3630066 (Open Web Text)

Max Activating Token Index: 896

Text #6

Max Range: 5.0542. Min Range: -5.0542

Max Act: 4.9873. Min Act: -0.1694

Data Index: 7095320 (Open Web Text)

Max Activating Token Index: 303

Text #7

Max Range: 5.0542. Min Range: -5.0542

Max Act: 4.9591. Min Act: -0.1700

Data Index: 7460050 (Open Web Text)

Max Activating Token Index: 8

Text #8

Max Range: 5.0542. Min Range: -5.0542

Max Act: 4.9468. Min Act: -0.1692

Data Index: 5588357 (Open Web Text)

Max Activating Token Index: 783

Text #9

Max Range: 5.0542. Min Range: -5.0542

Max Act: 4.9733. Min Act: -0.1700

Data Index: 3508739 (Open Web Text)

Max Activating Token Index: 23

Text #10

Max Range: 5.0542. Min Range: -5.0542

Max Act: 4.9162. Min Act: -0.1700

Data Index: 3661150 (Open Web Text)

Max Activating Token Index: 998

Text #11

Max Range: 5.0542. Min Range: -5.0542

Max Act: 4.9417. Min Act: -0.1699

Data Index: 6514389 (Open Web Text)

Max Activating Token Index: 31

Text #12

Max Range: 5.0542. Min Range: -5.0542

Max Act: 4.9071. Min Act: -0.1700

Data Index: 5165194 (Open Web Text)

Max Activating Token Index: 491

Text #13

Max Range: 5.0542. Min Range: -5.0542

Max Act: 4.9256. Min Act: -0.1700

Data Index: 6319456 (Open Web Text)

Max Activating Token Index: 366

Text #14

Max Range: 5.0542. Min Range: -5.0542

Max Act: 4.9234. Min Act: -0.1699

Data Index: 8214949 (Open Web Text)

Max Activating Token Index: 184

Text #15

Max Range: 5.0542. Min Range: -5.0542

Max Act: 4.8729. Min Act: -0.1699

Data Index: 5826429 (Open Web Text)

Max Activating Token Index: 5

Text #16

Max Range: 5.0542. Min Range: -5.0542

Max Act: 4.8833. Min Act: -0.1697

Data Index: 8642507 (Open Web Text)

Max Activating Token Index: 46

Text #17

Max Range: 5.0542. Min Range: -5.0542

Max Act: 4.9216. Min Act: -0.1700

Data Index: 4289673 (Open Web Text)

Max Activating Token Index: 609

Text #18

Max Range: 5.0542. Min Range: -5.0542

Max Act: 4.8934. Min Act: -0.1700

Data Index: 2248817 (Open Web Text)

Max Activating Token Index: 88

Text #19

Max Range: 5.0542. Min Range: -5.0542

Max Act: 4.8985. Min Act: -0.1700

Data Index: 6640202 (Open Web Text)

Max Activating Token Index: 901