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

Dataset: Open Web Text

Neuron 3066 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: 5.3991. Min Range: -5.3991

Max Act: 5.3991. Min Act: -0.1700

Data Index: 1066823 (Open Web Text)

Max Activating Token Index: 6

Text #1

Max Range: 5.3991. Min Range: -5.3991

Max Act: 5.2848. Min Act: -0.1700

Data Index: 3600294 (Open Web Text)

Max Activating Token Index: 5

Text #2

Max Range: 5.3991. Min Range: -5.3991

Max Act: 5.2423. Min Act: -0.1700

Data Index: 6409707 (Open Web Text)

Max Activating Token Index: 5

Text #3

Max Range: 5.3991. Min Range: -5.3991

Max Act: 5.2278. Min Act: -0.1700

Data Index: 192660 (Open Web Text)

Max Activating Token Index: 5

Text #4

Max Range: 5.3991. Min Range: -5.3991

Max Act: 5.2079. Min Act: -0.1700

Data Index: 8769886 (Open Web Text)

Max Activating Token Index: 8

Text #5

Max Range: 5.3991. Min Range: -5.3991

Max Act: 5.2303. Min Act: -0.1700

Data Index: 2648640 (Open Web Text)

Max Activating Token Index: 4

Text #6

Max Range: 5.3991. Min Range: -5.3991

Max Act: 5.2303. Min Act: -0.1700

Data Index: 397816 (Open Web Text)

Max Activating Token Index: 4

Text #7

Max Range: 5.3991. Min Range: -5.3991

Max Act: 5.2081. Min Act: -0.1700

Data Index: 4477520 (Open Web Text)

Max Activating Token Index: 6

Text #8

Max Range: 5.3991. Min Range: -5.3991

Max Act: 5.2119. Min Act: -0.1700

Data Index: 3422370 (Open Web Text)

Max Activating Token Index: 5

Text #9

Max Range: 5.3991. Min Range: -5.3991

Max Act: 5.1840. Min Act: -0.1700

Data Index: 7342079 (Open Web Text)

Max Activating Token Index: 4

Text #10

Max Range: 5.3991. Min Range: -5.3991

Max Act: 5.1920. Min Act: -0.1700

Data Index: 347963 (Open Web Text)

Max Activating Token Index: 7

Text #11

Max Range: 5.3991. Min Range: -5.3991

Max Act: 5.1828. Min Act: -0.1700

Data Index: 4850519 (Open Web Text)

Max Activating Token Index: 5

Text #12

Max Range: 5.3991. Min Range: -5.3991

Max Act: 5.1916. Min Act: -0.1700

Data Index: 562480 (Open Web Text)

Max Activating Token Index: 3

Text #13

Max Range: 5.3991. Min Range: -5.3991

Max Act: 5.1916. Min Act: -0.1700

Data Index: 6937070 (Open Web Text)

Max Activating Token Index: 5

Text #14

Max Range: 5.3991. Min Range: -5.3991

Max Act: 5.1812. Min Act: -0.1700

Data Index: 4014482 (Open Web Text)

Max Activating Token Index: 4

Text #15

Max Range: 5.3991. Min Range: -5.3991

Max Act: 5.1572. Min Act: -0.1700

Data Index: 3367321 (Open Web Text)

Max Activating Token Index: 7

Text #16

Max Range: 5.3991. Min Range: -5.3991

Max Act: 5.1469. Min Act: -0.1700

Data Index: 4704389 (Open Web Text)

Max Activating Token Index: 6

Text #17

Max Range: 5.3991. Min Range: -5.3991

Max Act: 5.1755. Min Act: -0.1700

Data Index: 1244526 (Open Web Text)

Max Activating Token Index: 7

Text #18

Max Range: 5.3991. Min Range: -5.3991

Max Act: 5.1554. Min Act: -0.1700

Data Index: 96964 (Open Web Text)

Max Activating Token Index: 5

Text #19

Max Range: 5.3991. Min Range: -5.3991

Max Act: 5.1481. Min Act: -0.1700

Data Index: 3432177 (Open Web Text)

Max Activating Token Index: 4