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

Dataset: Open Web Text

Neuron 292 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: 5.3672. Min Range: -5.3672

Max Act: 5.3672. Min Act: -0.1700

Data Index: 3202614 (Open Web Text)

Max Activating Token Index: 5

Text #1

Max Range: 5.3672. Min Range: -5.3672

Max Act: 5.3056. Min Act: -0.1700

Data Index: 96755 (Open Web Text)

Max Activating Token Index: 6

Text #2

Max Range: 5.3672. Min Range: -5.3672

Max Act: 5.2852. Min Act: -0.1700

Data Index: 1685792 (Open Web Text)

Max Activating Token Index: 6

Text #3

Max Range: 5.3672. Min Range: -5.3672

Max Act: 5.2714. Min Act: -0.1700

Data Index: 4940546 (Open Web Text)

Max Activating Token Index: 8

Text #4

Max Range: 5.3672. Min Range: -5.3672

Max Act: 5.2798. Min Act: -0.1700

Data Index: 5837950 (Open Web Text)

Max Activating Token Index: 8

Text #5

Max Range: 5.3672. Min Range: -5.3672

Max Act: 5.2794. Min Act: -0.1700

Data Index: 8507955 (Open Web Text)

Max Activating Token Index: 6

Text #6

Max Range: 5.3672. Min Range: -5.3672

Max Act: 5.3070. Min Act: -0.1700

Data Index: 1710711 (Open Web Text)

Max Activating Token Index: 5

Text #7

Max Range: 5.3672. Min Range: -5.3672

Max Act: 5.2986. Min Act: -0.1700

Data Index: 6758832 (Open Web Text)

Max Activating Token Index: 6

Text #8

Max Range: 5.3672. Min Range: -5.3672

Max Act: 5.2525. Min Act: -0.1700

Data Index: 6638489 (Open Web Text)

Max Activating Token Index: 6

Text #9

Max Range: 5.3672. Min Range: -5.3672

Max Act: 5.2564. Min Act: -0.1700

Data Index: 1558845 (Open Web Text)

Max Activating Token Index: 5

Text #10

Max Range: 5.3672. Min Range: -5.3672

Max Act: 5.2451. Min Act: -0.1700

Data Index: 2186280 (Open Web Text)

Max Activating Token Index: 6

Text #11

Max Range: 5.3672. Min Range: -5.3672

Max Act: 5.2556. Min Act: -0.1700

Data Index: 8605326 (Open Web Text)

Max Activating Token Index: 4

Text #12

Max Range: 5.3672. Min Range: -5.3672

Max Act: 5.2501. Min Act: -0.1700

Data Index: 8392602 (Open Web Text)

Max Activating Token Index: 8

Text #13

Max Range: 5.3672. Min Range: -5.3672

Max Act: 5.2471. Min Act: -0.1700

Data Index: 8181177 (Open Web Text)

Max Activating Token Index: 6

Text #14

Max Range: 5.3672. Min Range: -5.3672

Max Act: 5.2611. Min Act: -0.1700

Data Index: 6892085 (Open Web Text)

Max Activating Token Index: 6

Text #15

Max Range: 5.3672. Min Range: -5.3672

Max Act: 5.2504. Min Act: -0.1700

Data Index: 6029512 (Open Web Text)

Max Activating Token Index: 6

Text #16

Max Range: 5.3672. Min Range: -5.3672

Max Act: 5.2726. Min Act: -0.1700

Data Index: 4940106 (Open Web Text)

Max Activating Token Index: 4

Text #17

Max Range: 5.3672. Min Range: -5.3672

Max Act: 5.2556. Min Act: -0.1700

Data Index: 593192 (Open Web Text)

Max Activating Token Index: 4

Text #18

Max Range: 5.3672. Min Range: -5.3672

Max Act: 5.2521. Min Act: -0.1700

Data Index: 4210343 (Open Web Text)

Max Activating Token Index: 7

Text #19

Max Range: 5.3672. Min Range: -5.3672

Max Act: 5.2474. Min Act: -0.1700

Data Index: 1402731 (Open Web Text)

Max Activating Token Index: 5