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

Dataset: Open Web Text

Neuron 1646 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: 4.4873. Min Range: -4.4873

Max Act: 4.4873. Min Act: -0.1700

Data Index: 7202990 (Open Web Text)

Max Activating Token Index: 6

Text #1

Max Range: 4.4873. Min Range: -4.4873

Max Act: 4.4767. Min Act: -0.1700

Data Index: 6936000 (Open Web Text)

Max Activating Token Index: 7

Text #2

Max Range: 4.4873. Min Range: -4.4873

Max Act: 4.4738. Min Act: -0.1700

Data Index: 1377805 (Open Web Text)

Max Activating Token Index: 759

Text #3

Max Range: 4.4873. Min Range: -4.4873

Max Act: 4.4316. Min Act: -0.1700

Data Index: 8202331 (Open Web Text)

Max Activating Token Index: 6

Text #4

Max Range: 4.4873. Min Range: -4.4873

Max Act: 4.4249. Min Act: -0.1700

Data Index: 164174 (Open Web Text)

Max Activating Token Index: 4

Text #5

Max Range: 4.4873. Min Range: -4.4873

Max Act: 4.3996. Min Act: -0.1700

Data Index: 1320436 (Open Web Text)

Max Activating Token Index: 8

Text #6

Max Range: 4.4873. Min Range: -4.4873

Max Act: 4.3741. Min Act: -0.1700

Data Index: 7174499 (Open Web Text)

Max Activating Token Index: 3

Text #7

Max Range: 4.4873. Min Range: -4.4873

Max Act: 4.3983. Min Act: -0.1700

Data Index: 6102566 (Open Web Text)

Max Activating Token Index: 12

Text #8

Max Range: 4.4873. Min Range: -4.4873

Max Act: 4.3671. Min Act: -0.1700

Data Index: 7822114 (Open Web Text)

Max Activating Token Index: 5

Text #9

Max Range: 4.4873. Min Range: -4.4873

Max Act: 4.3813. Min Act: -0.1700

Data Index: 1521603 (Open Web Text)

Max Activating Token Index: 878

Text #10

Max Range: 4.4873. Min Range: -4.4873

Max Act: 4.3659. Min Act: -0.1700

Data Index: 7665336 (Open Web Text)

Max Activating Token Index: 5

Text #11

Max Range: 4.4873. Min Range: -4.4873

Max Act: 4.3408. Min Act: -0.1700

Data Index: 1207690 (Open Web Text)

Max Activating Token Index: 5

Text #12

Max Range: 4.4873. Min Range: -4.4873

Max Act: 4.3791. Min Act: -0.1700

Data Index: 3476286 (Open Web Text)

Max Activating Token Index: 4

Text #13

Max Range: 4.4873. Min Range: -4.4873

Max Act: 4.3376. Min Act: -0.1700

Data Index: 7605158 (Open Web Text)

Max Activating Token Index: 5

Text #14

Max Range: 4.4873. Min Range: -4.4873

Max Act: 4.3372. Min Act: -0.1700

Data Index: 7462712 (Open Web Text)

Max Activating Token Index: 5

Text #15

Max Range: 4.4873. Min Range: -4.4873

Max Act: 4.3217. Min Act: -0.1700

Data Index: 3503421 (Open Web Text)

Max Activating Token Index: 10

Text #16

Max Range: 4.4873. Min Range: -4.4873

Max Act: 4.3306. Min Act: -0.1700

Data Index: 7401927 (Open Web Text)

Max Activating Token Index: 5

Text #17

Max Range: 4.4873. Min Range: -4.4873

Max Act: 4.3509. Min Act: -0.1700

Data Index: 1665689 (Open Web Text)

Max Activating Token Index: 7

Text #18

Max Range: 4.4873. Min Range: -4.4873

Max Act: 4.3313. Min Act: -0.1700

Data Index: 3249075 (Open Web Text)

Max Activating Token Index: 8

Text #19

Max Range: 4.4873. Min Range: -4.4873

Max Act: 4.3232. Min Act: -0.1700

Data Index: 5450834 (Open Web Text)

Max Activating Token Index: 11