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

Dataset: Open Web Text

Neuron 2097 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: 1.2749. Min Range: -1.2749

Max Act: 1.2749. Min Act: -0.1700

Data Index: 3058901 (Open Web Text)

Max Activating Token Index: 9

Text #1

Max Range: 1.2749. Min Range: -1.2749

Max Act: 1.2277. Min Act: -0.1700

Data Index: 7595925 (Open Web Text)

Max Activating Token Index: 15

Text #2

Max Range: 1.2749. Min Range: -1.2749

Max Act: 1.1646. Min Act: -0.1700

Data Index: 5352121 (Open Web Text)

Max Activating Token Index: 9

Text #3

Max Range: 1.2749. Min Range: -1.2749

Max Act: 1.1432. Min Act: -0.1700

Data Index: 3597978 (Open Web Text)

Max Activating Token Index: 12

Text #4

Max Range: 1.2749. Min Range: -1.2749

Max Act: 1.1044. Min Act: -0.1700

Data Index: 5769005 (Open Web Text)

Max Activating Token Index: 27

Text #5

Max Range: 1.2749. Min Range: -1.2749

Max Act: 1.1071. Min Act: -0.1700

Data Index: 2574358 (Open Web Text)

Max Activating Token Index: 18

Text #6

Max Range: 1.2749. Min Range: -1.2749

Max Act: 1.1154. Min Act: -0.1700

Data Index: 481073 (Open Web Text)

Max Activating Token Index: 12

Text #7

Max Range: 1.2749. Min Range: -1.2749

Max Act: 1.1068. Min Act: -0.1700

Data Index: 5552594 (Open Web Text)

Max Activating Token Index: 11

Text #8

Max Range: 1.2749. Min Range: -1.2749

Max Act: 1.1001. Min Act: -0.1700

Data Index: 4508491 (Open Web Text)

Max Activating Token Index: 8

Text #9

Max Range: 1.2749. Min Range: -1.2749

Max Act: 1.0878. Min Act: -0.1700

Data Index: 7627455 (Open Web Text)

Max Activating Token Index: 10

Text #10

Max Range: 1.2749. Min Range: -1.2749

Max Act: 1.0733. Min Act: -0.1700

Data Index: 5153748 (Open Web Text)

Max Activating Token Index: 10

Text #11

Max Range: 1.2749. Min Range: -1.2749

Max Act: 1.0763. Min Act: -0.1700

Data Index: 3342304 (Open Web Text)

Max Activating Token Index: 16

Text #12

Max Range: 1.2749. Min Range: -1.2749

Max Act: 1.0506. Min Act: -0.1700

Data Index: 6670868 (Open Web Text)

Max Activating Token Index: 17

Text #13

Max Range: 1.2749. Min Range: -1.2749

Max Act: 1.0593. Min Act: -0.1700

Data Index: 2154922 (Open Web Text)

Max Activating Token Index: 13

Text #14

Max Range: 1.2749. Min Range: -1.2749

Max Act: 1.0656. Min Act: -0.1700

Data Index: 5948243 (Open Web Text)

Max Activating Token Index: 10

Text #15

Max Range: 1.2749. Min Range: -1.2749

Max Act: 1.0540. Min Act: -0.1700

Data Index: 190097 (Open Web Text)

Max Activating Token Index: 7

Text #16

Max Range: 1.2749. Min Range: -1.2749

Max Act: 1.0691. Min Act: -0.1700

Data Index: 6456436 (Open Web Text)

Max Activating Token Index: 14

Text #17

Max Range: 1.2749. Min Range: -1.2749

Max Act: 1.0573. Min Act: -0.1700

Data Index: 7864972 (Open Web Text)

Max Activating Token Index: 16

Text #18

Max Range: 1.2749. Min Range: -1.2749

Max Act: 1.0624. Min Act: -0.1700

Data Index: 6775704 (Open Web Text)

Max Activating Token Index: 8

Text #19

Max Range: 1.2749. Min Range: -1.2749

Max Act: 1.0305. Min Act: -0.1700

Data Index: 1329835 (Open Web Text)

Max Activating Token Index: 12