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

Dataset: Open Web Text

Neuron 1880 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: 3.7021. Min Range: -3.7021

Max Act: 3.7021. Min Act: -0.1700

Data Index: 8678397 (Open Web Text)

Max Activating Token Index: 3

Text #1

Max Range: 3.7021. Min Range: -3.7021

Max Act: 3.5752. Min Act: -0.1700

Data Index: 1055793 (Open Web Text)

Max Activating Token Index: 3

Text #2

Max Range: 3.7021. Min Range: -3.7021

Max Act: 3.5884. Min Act: -0.1700

Data Index: 528993 (Open Web Text)

Max Activating Token Index: 2

Text #3

Max Range: 3.7021. Min Range: -3.7021

Max Act: 3.5884. Min Act: -0.1700

Data Index: 6613221 (Open Web Text)

Max Activating Token Index: 2

Text #4

Max Range: 3.7021. Min Range: -3.7021

Max Act: 3.5834. Min Act: -0.1700

Data Index: 1208570 (Open Web Text)

Max Activating Token Index: 5

Text #5

Max Range: 3.7021. Min Range: -3.7021

Max Act: 3.5038. Min Act: -0.1700

Data Index: 1089039 (Open Web Text)

Max Activating Token Index: 3

Text #6

Max Range: 3.7021. Min Range: -3.7021

Max Act: 3.5038. Min Act: -0.1700

Data Index: 2300111 (Open Web Text)

Max Activating Token Index: 3

Text #7

Max Range: 3.7021. Min Range: -3.7021

Max Act: 3.4903. Min Act: -0.1700

Data Index: 1547503 (Open Web Text)

Max Activating Token Index: 7

Text #8

Max Range: 3.7021. Min Range: -3.7021

Max Act: 3.4727. Min Act: -0.1700

Data Index: 7557088 (Open Web Text)

Max Activating Token Index: 38

Text #9

Max Range: 3.7021. Min Range: -3.7021

Max Act: 3.5038. Min Act: -0.1700

Data Index: 1988366 (Open Web Text)

Max Activating Token Index: 3

Text #10

Max Range: 3.7021. Min Range: -3.7021

Max Act: 3.4483. Min Act: -0.1700

Data Index: 8651019 (Open Web Text)

Max Activating Token Index: 546

Text #11

Max Range: 3.7021. Min Range: -3.7021

Max Act: 3.4451. Min Act: -0.1700

Data Index: 7776041 (Open Web Text)

Max Activating Token Index: 5

Text #12

Max Range: 3.7021. Min Range: -3.7021

Max Act: 3.4348. Min Act: -0.1700

Data Index: 4517346 (Open Web Text)

Max Activating Token Index: 2

Text #13

Max Range: 3.7021. Min Range: -3.7021

Max Act: 3.4267. Min Act: -0.1700

Data Index: 1611839 (Open Web Text)

Max Activating Token Index: 2

Text #14

Max Range: 3.7021. Min Range: -3.7021

Max Act: 3.4348. Min Act: -0.1700

Data Index: 3746518 (Open Web Text)

Max Activating Token Index: 2

Text #15

Max Range: 3.7021. Min Range: -3.7021

Max Act: 3.4267. Min Act: -0.1700

Data Index: 7328978 (Open Web Text)

Max Activating Token Index: 2

Text #16

Max Range: 3.7021. Min Range: -3.7021

Max Act: 3.4298. Min Act: -0.1700

Data Index: 3257237 (Open Web Text)

Max Activating Token Index: 2

Text #17

Max Range: 3.7021. Min Range: -3.7021

Max Act: 3.4207. Min Act: -0.1700

Data Index: 7257249 (Open Web Text)

Max Activating Token Index: 7

Text #18

Max Range: 3.7021. Min Range: -3.7021

Max Act: 3.4331. Min Act: -0.1700

Data Index: 6870944 (Open Web Text)

Max Activating Token Index: 2

Text #19

Max Range: 3.7021. Min Range: -3.7021

Max Act: 3.4298. Min Act: -0.1700

Data Index: 2297874 (Open Web Text)

Max Activating Token Index: 2