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

Dataset: Open Web Text

Neuron 885 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: 3.2393. Min Range: -3.2393

Max Act: 3.2393. Min Act: -0.1700

Data Index: 1064266 (Open Web Text)

Max Activating Token Index: 5

Text #1

Max Range: 3.2393. Min Range: -3.2393

Max Act: 3.2070. Min Act: -0.1700

Data Index: 7401126 (Open Web Text)

Max Activating Token Index: 22

Text #2

Max Range: 3.2393. Min Range: -3.2393

Max Act: 3.1776. Min Act: -0.1700

Data Index: 7300364 (Open Web Text)

Max Activating Token Index: 47

Text #3

Max Range: 3.2393. Min Range: -3.2393

Max Act: 3.1188. Min Act: -0.1700

Data Index: 3324749 (Open Web Text)

Max Activating Token Index: 15

Text #4

Max Range: 3.2393. Min Range: -3.2393

Max Act: 3.1197. Min Act: -0.1700

Data Index: 6046077 (Open Web Text)

Max Activating Token Index: 3

Text #5

Max Range: 3.2393. Min Range: -3.2393

Max Act: 3.1024. Min Act: -0.1700

Data Index: 2826625 (Open Web Text)

Max Activating Token Index: 9

Text #6

Max Range: 3.2393. Min Range: -3.2393

Max Act: 3.0974. Min Act: -0.1700

Data Index: 5531590 (Open Web Text)

Max Activating Token Index: 28

Text #7

Max Range: 3.2393. Min Range: -3.2393

Max Act: 3.0946. Min Act: -0.1700

Data Index: 3432946 (Open Web Text)

Max Activating Token Index: 42

Text #8

Max Range: 3.2393. Min Range: -3.2393

Max Act: 3.0973. Min Act: -0.1700

Data Index: 7007245 (Open Web Text)

Max Activating Token Index: 115

Text #9

Max Range: 3.2393. Min Range: -3.2393

Max Act: 3.0930. Min Act: -0.1700

Data Index: 4705952 (Open Web Text)

Max Activating Token Index: 419

Text #10

Max Range: 3.2393. Min Range: -3.2393

Max Act: 3.0619. Min Act: -0.1700

Data Index: 7008602 (Open Web Text)

Max Activating Token Index: 3

Text #11

Max Range: 3.2393. Min Range: -3.2393

Max Act: 3.0655. Min Act: -0.1700

Data Index: 5809347 (Open Web Text)

Max Activating Token Index: 43

Text #12

Max Range: 3.2393. Min Range: -3.2393

Max Act: 3.0797. Min Act: -0.1700

Data Index: 2971794 (Open Web Text)

Max Activating Token Index: 4

Text #13

Max Range: 3.2393. Min Range: -3.2393

Max Act: 3.0772. Min Act: -0.1700

Data Index: 6445820 (Open Web Text)

Max Activating Token Index: 78

Text #14

Max Range: 3.2393. Min Range: -3.2393

Max Act: 3.0762. Min Act: -0.1700

Data Index: 1988564 (Open Web Text)

Max Activating Token Index: 4

Text #15

Max Range: 3.2393. Min Range: -3.2393

Max Act: 3.0787. Min Act: -0.1700

Data Index: 2134049 (Open Web Text)

Max Activating Token Index: 6

Text #16

Max Range: 3.2393. Min Range: -3.2393

Max Act: 3.0798. Min Act: -0.1700

Data Index: 809995 (Open Web Text)

Max Activating Token Index: 17

Text #17

Max Range: 3.2393. Min Range: -3.2393

Max Act: 3.0759. Min Act: -0.1700

Data Index: 6717659 (Open Web Text)

Max Activating Token Index: 284

Text #18

Max Range: 3.2393. Min Range: -3.2393

Max Act: 3.0701. Min Act: -0.1700

Data Index: 2874947 (Open Web Text)

Max Activating Token Index: 5

Text #19

Max Range: 3.2393. Min Range: -3.2393

Max Act: 3.0587. Min Act: -0.1700

Data Index: 3140170 (Open Web Text)

Max Activating Token Index: 33