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

Dataset: Open Web Text

Neuron 2807 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: 1.6616. Min Range: -1.6616

Max Act: 1.6559. Min Act: -0.1700

Data Index: 4661294 (Open Web Text)

Max Activating Token Index: 1023

Text #1

Max Range: 1.6616. Min Range: -1.6616

Max Act: 1.6616. Min Act: -0.1700

Data Index: 7484532 (Open Web Text)

Max Activating Token Index: 418

Text #2

Max Range: 1.6616. Min Range: -1.6616

Max Act: 1.6534. Min Act: -0.1700

Data Index: 815092 (Open Web Text)

Max Activating Token Index: 10

Text #3

Max Range: 1.6616. Min Range: -1.6616

Max Act: 1.6441. Min Act: -0.1700

Data Index: 4711103 (Open Web Text)

Max Activating Token Index: 844

Text #4

Max Range: 1.6616. Min Range: -1.6616

Max Act: 1.6503. Min Act: -0.1700

Data Index: 3320311 (Open Web Text)

Max Activating Token Index: 1023

Text #5

Max Range: 1.6616. Min Range: -1.6616

Max Act: 1.6297. Min Act: -0.1700

Data Index: 2474973 (Open Web Text)

Max Activating Token Index: 2

Text #6

Max Range: 1.6616. Min Range: -1.6616

Max Act: 1.6149. Min Act: -0.1700

Data Index: 7839535 (Open Web Text)

Max Activating Token Index: 2

Text #7

Max Range: 1.6616. Min Range: -1.6616

Max Act: 1.6148. Min Act: -0.1700

Data Index: 696589 (Open Web Text)

Max Activating Token Index: 215

Text #8

Max Range: 1.6616. Min Range: -1.6616

Max Act: 1.6100. Min Act: -0.1699

Data Index: 5595459 (Open Web Text)

Max Activating Token Index: 3

Text #9

Max Range: 1.6616. Min Range: -1.6616

Max Act: 1.6055. Min Act: -0.1700

Data Index: 5124958 (Open Web Text)

Max Activating Token Index: 7

Text #10

Max Range: 1.6616. Min Range: -1.6616

Max Act: 1.5956. Min Act: -0.1700

Data Index: 5726450 (Open Web Text)

Max Activating Token Index: 1023

Text #11

Max Range: 1.6616. Min Range: -1.6616

Max Act: 1.5986. Min Act: -0.1700

Data Index: 15412 (Open Web Text)

Max Activating Token Index: 10

Text #12

Max Range: 1.6616. Min Range: -1.6616

Max Act: 1.6086. Min Act: -0.1699

Data Index: 4168852 (Open Web Text)

Max Activating Token Index: 1023

Text #13

Max Range: 1.6616. Min Range: -1.6616

Max Act: 1.5929. Min Act: -0.1700

Data Index: 7446127 (Open Web Text)

Max Activating Token Index: 844

Text #14

Max Range: 1.6616. Min Range: -1.6616

Max Act: 1.5891. Min Act: -0.1700

Data Index: 5814778 (Open Web Text)

Max Activating Token Index: 5

Text #15

Max Range: 1.6616. Min Range: -1.6616

Max Act: 1.5844. Min Act: -0.1700

Data Index: 6164031 (Open Web Text)

Max Activating Token Index: 585

Text #16

Max Range: 1.6616. Min Range: -1.6616

Max Act: 1.5910. Min Act: -0.1700

Data Index: 1047426 (Open Web Text)

Max Activating Token Index: 3

Text #17

Max Range: 1.6616. Min Range: -1.6616

Max Act: 1.5947. Min Act: -0.1700

Data Index: 4358706 (Open Web Text)

Max Activating Token Index: 1023

Text #18

Max Range: 1.6616. Min Range: -1.6616

Max Act: 1.5848. Min Act: -0.1700

Data Index: 6686902 (Open Web Text)

Max Activating Token Index: 2

Text #19

Max Range: 1.6616. Min Range: -1.6616

Max Act: 1.5870. Min Act: -0.1700

Data Index: 6445382 (Open Web Text)

Max Activating Token Index: 16