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

Dataset: Open Web Text

Neuron 3005 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: 3.1065. Min Range: -3.1065

Max Act: 3.1065. Min Act: -0.1700

Data Index: 1978235 (Open Web Text)

Max Activating Token Index: 16

Text #1

Max Range: 3.1065. Min Range: -3.1065

Max Act: 3.0895. Min Act: -0.1700

Data Index: 6069813 (Open Web Text)

Max Activating Token Index: 3

Text #2

Max Range: 3.1065. Min Range: -3.1065

Max Act: 3.0569. Min Act: -0.1700

Data Index: 4200214 (Open Web Text)

Max Activating Token Index: 3

Text #3

Max Range: 3.1065. Min Range: -3.1065

Max Act: 3.0569. Min Act: -0.1700

Data Index: 1530655 (Open Web Text)

Max Activating Token Index: 3

Text #4

Max Range: 3.1065. Min Range: -3.1065

Max Act: 3.0718. Min Act: -0.1700

Data Index: 4125202 (Open Web Text)

Max Activating Token Index: 4

Text #5

Max Range: 3.1065. Min Range: -3.1065

Max Act: 3.0569. Min Act: -0.1700

Data Index: 8519626 (Open Web Text)

Max Activating Token Index: 3

Text #6

Max Range: 3.1065. Min Range: -3.1065

Max Act: 3.0022. Min Act: -0.1700

Data Index: 1782206 (Open Web Text)

Max Activating Token Index: 5

Text #7

Max Range: 3.1065. Min Range: -3.1065

Max Act: 2.9910. Min Act: -0.1700

Data Index: 3666884 (Open Web Text)

Max Activating Token Index: 3

Text #8

Max Range: 3.1065. Min Range: -3.1065

Max Act: 2.9875. Min Act: -0.1700

Data Index: 815331 (Open Web Text)

Max Activating Token Index: 4

Text #9

Max Range: 3.1065. Min Range: -3.1065

Max Act: 2.9786. Min Act: -0.1700

Data Index: 4463269 (Open Web Text)

Max Activating Token Index: 5

Text #10

Max Range: 3.1065. Min Range: -3.1065

Max Act: 2.9784. Min Act: -0.1700

Data Index: 1090251 (Open Web Text)

Max Activating Token Index: 5

Text #11

Max Range: 3.1065. Min Range: -3.1065

Max Act: 2.9520. Min Act: -0.1700

Data Index: 4182847 (Open Web Text)

Max Activating Token Index: 2

Text #12

Max Range: 3.1065. Min Range: -3.1065

Max Act: 2.9622. Min Act: -0.1700

Data Index: 2871595 (Open Web Text)

Max Activating Token Index: 5

Text #13

Max Range: 3.1065. Min Range: -3.1065

Max Act: 2.9571. Min Act: -0.1700

Data Index: 4602838 (Open Web Text)

Max Activating Token Index: 4

Text #14

Max Range: 3.1065. Min Range: -3.1065

Max Act: 2.9674. Min Act: -0.1700

Data Index: 83661 (Open Web Text)

Max Activating Token Index: 3

Text #15

Max Range: 3.1065. Min Range: -3.1065

Max Act: 2.9606. Min Act: -0.1700

Data Index: 4361139 (Open Web Text)

Max Activating Token Index: 5

Text #16

Max Range: 3.1065. Min Range: -3.1065

Max Act: 2.9331. Min Act: -0.1700

Data Index: 1956800 (Open Web Text)

Max Activating Token Index: 12

Text #17

Max Range: 3.1065. Min Range: -3.1065

Max Act: 2.9432. Min Act: -0.1700

Data Index: 3338146 (Open Web Text)

Max Activating Token Index: 6

Text #18

Max Range: 3.1065. Min Range: -3.1065

Max Act: 2.9369. Min Act: -0.1700

Data Index: 3521162 (Open Web Text)

Max Activating Token Index: 3

Text #19

Max Range: 3.1065. Min Range: -3.1065

Max Act: 2.9369. Min Act: -0.1700

Data Index: 684875 (Open Web Text)

Max Activating Token Index: 3