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

Dataset: Open Web Text

Neuron 2873 in Layer 0

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: 3.3153. Min Range: -3.3153

Max Act: 3.3153. Min Act: -0.1700

Data Index: 4887068 (Open Web Text)

Max Activating Token Index: 29

Text #1

Max Range: 3.3153. Min Range: -3.3153

Max Act: 3.2652. Min Act: -0.1700

Data Index: 2018003 (Open Web Text)

Max Activating Token Index: 717

Text #2

Max Range: 3.3153. Min Range: -3.3153

Max Act: 3.2237. Min Act: -0.1700

Data Index: 571758 (Open Web Text)

Max Activating Token Index: 610

Text #3

Max Range: 3.3153. Min Range: -3.3153

Max Act: 3.2183. Min Act: -0.1700

Data Index: 6479182 (Open Web Text)

Max Activating Token Index: 549

Text #4

Max Range: 3.3153. Min Range: -3.3153

Max Act: 3.1841. Min Act: -0.1700

Data Index: 8698661 (Open Web Text)

Max Activating Token Index: 481

Text #5

Max Range: 3.3153. Min Range: -3.3153

Max Act: 3.1726. Min Act: -0.1700

Data Index: 5102154 (Open Web Text)

Max Activating Token Index: 379

Text #6

Max Range: 3.3153. Min Range: -3.3153

Max Act: 3.2014. Min Act: -0.1700

Data Index: 5163064 (Open Web Text)

Max Activating Token Index: 45

Text #7

Max Range: 3.3153. Min Range: -3.3153

Max Act: 3.1878. Min Act: -0.1700

Data Index: 7152665 (Open Web Text)

Max Activating Token Index: 723

Text #8

Max Range: 3.3153. Min Range: -3.3153

Max Act: 3.1868. Min Act: -0.1700

Data Index: 4004041 (Open Web Text)

Max Activating Token Index: 448

Text #9

Max Range: 3.3153. Min Range: -3.3153

Max Act: 3.1638. Min Act: -0.1700

Data Index: 7268961 (Open Web Text)

Max Activating Token Index: 610

Text #10

Max Range: 3.3153. Min Range: -3.3153

Max Act: 3.1449. Min Act: -0.1700

Data Index: 6980972 (Open Web Text)

Max Activating Token Index: 689

Text #11

Max Range: 3.3153. Min Range: -3.3153

Max Act: 3.1659. Min Act: -0.1700

Data Index: 4466877 (Open Web Text)

Max Activating Token Index: 931

Text #12

Max Range: 3.3153. Min Range: -3.3153

Max Act: 3.1647. Min Act: -0.1700

Data Index: 4044065 (Open Web Text)

Max Activating Token Index: 409

Text #13

Max Range: 3.3153. Min Range: -3.3153

Max Act: 3.1719. Min Act: -0.1700

Data Index: 6147970 (Open Web Text)

Max Activating Token Index: 684

Text #14

Max Range: 3.3153. Min Range: -3.3153

Max Act: 3.1538. Min Act: -0.1700

Data Index: 5612191 (Open Web Text)

Max Activating Token Index: 637

Text #15

Max Range: 3.3153. Min Range: -3.3153

Max Act: 3.1576. Min Act: -0.1700

Data Index: 760268 (Open Web Text)

Max Activating Token Index: 856

Text #16

Max Range: 3.3153. Min Range: -3.3153

Max Act: 3.1568. Min Act: -0.1700

Data Index: 5326447 (Open Web Text)

Max Activating Token Index: 645

Text #17

Max Range: 3.3153. Min Range: -3.3153

Max Act: 3.1484. Min Act: -0.1700

Data Index: 3898798 (Open Web Text)

Max Activating Token Index: 41

Text #18

Max Range: 3.3153. Min Range: -3.3153

Max Act: 3.1448. Min Act: -0.1700

Data Index: 5305478 (Open Web Text)

Max Activating Token Index: 459

Text #19

Max Range: 3.3153. Min Range: -3.3153

Max Act: 3.1572. Min Act: -0.1700

Data Index: 3893654 (Open Web Text)

Max Activating Token Index: 158