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

Dataset: Open Web Text

Neuron 1494 in Layer 3

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: 4.1880. Min Range: -4.1880

Max Act: 4.1880. Min Act: -0.1700

Data Index: 3010472 (Open Web Text)

Max Activating Token Index: 532

Text #1

Max Range: 4.1880. Min Range: -4.1880

Max Act: 4.1259. Min Act: -0.1700

Data Index: 8198982 (Open Web Text)

Max Activating Token Index: 291

Text #2

Max Range: 4.1880. Min Range: -4.1880

Max Act: 4.0760. Min Act: -0.1700

Data Index: 7890933 (Open Web Text)

Max Activating Token Index: 288

Text #3

Max Range: 4.1880. Min Range: -4.1880

Max Act: 4.1194. Min Act: -0.1700

Data Index: 3392466 (Open Web Text)

Max Activating Token Index: 1007

Text #4

Max Range: 4.1880. Min Range: -4.1880

Max Act: 4.0664. Min Act: -0.1700

Data Index: 8201719 (Open Web Text)

Max Activating Token Index: 703

Text #5

Max Range: 4.1880. Min Range: -4.1880

Max Act: 4.0739. Min Act: -0.1700

Data Index: 3368146 (Open Web Text)

Max Activating Token Index: 50

Text #6

Max Range: 4.1880. Min Range: -4.1880

Max Act: 4.1123. Min Act: -0.1700

Data Index: 7240259 (Open Web Text)

Max Activating Token Index: 576

Text #7

Max Range: 4.1880. Min Range: -4.1880

Max Act: 4.0645. Min Act: -0.1700

Data Index: 3219713 (Open Web Text)

Max Activating Token Index: 352

Text #8

Max Range: 4.1880. Min Range: -4.1880

Max Act: 4.0318. Min Act: -0.1700

Data Index: 2783416 (Open Web Text)

Max Activating Token Index: 31

Text #9

Max Range: 4.1880. Min Range: -4.1880

Max Act: 4.0622. Min Act: -0.1700

Data Index: 3854198 (Open Web Text)

Max Activating Token Index: 49

Text #10

Max Range: 4.1880. Min Range: -4.1880

Max Act: 4.0463. Min Act: -0.1700

Data Index: 6135547 (Open Web Text)

Max Activating Token Index: 613

Text #11

Max Range: 4.1880. Min Range: -4.1880

Max Act: 4.0355. Min Act: -0.1700

Data Index: 195323 (Open Web Text)

Max Activating Token Index: 80

Text #12

Max Range: 4.1880. Min Range: -4.1880

Max Act: 4.0527. Min Act: -0.1700

Data Index: 5366711 (Open Web Text)

Max Activating Token Index: 395

Text #13

Max Range: 4.1880. Min Range: -4.1880

Max Act: 4.0188. Min Act: -0.1700

Data Index: 1730902 (Open Web Text)

Max Activating Token Index: 860

Text #14

Max Range: 4.1880. Min Range: -4.1880

Max Act: 4.0193. Min Act: -0.1700

Data Index: 6244199 (Open Web Text)

Max Activating Token Index: 36

Text #15

Max Range: 4.1880. Min Range: -4.1880

Max Act: 4.0303. Min Act: -0.1700

Data Index: 2572922 (Open Web Text)

Max Activating Token Index: 915

Text #16

Max Range: 4.1880. Min Range: -4.1880

Max Act: 4.0234. Min Act: -0.1700

Data Index: 4337455 (Open Web Text)

Max Activating Token Index: 123

Text #17

Max Range: 4.1880. Min Range: -4.1880

Max Act: 4.0106. Min Act: -0.1700

Data Index: 2014068 (Open Web Text)

Max Activating Token Index: 762

Text #18

Max Range: 4.1880. Min Range: -4.1880

Max Act: 3.9740. Min Act: -0.1700

Data Index: 6771584 (Open Web Text)

Max Activating Token Index: 861

Text #19

Max Range: 4.1880. Min Range: -4.1880

Max Act: 3.9870. Min Act: -0.1700

Data Index: 7499599 (Open Web Text)

Max Activating Token Index: 1007