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

Dataset: Open Web Text

Neuron 23 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: 5.9665. Min Range: -5.9665

Max Act: 5.9665. Min Act: -0.1700

Data Index: 5307246 (Open Web Text)

Max Activating Token Index: 17

Text #1

Max Range: 5.9665. Min Range: -5.9665

Max Act: 5.9313. Min Act: -0.1700

Data Index: 8688718 (Open Web Text)

Max Activating Token Index: 6

Text #2

Max Range: 5.9665. Min Range: -5.9665

Max Act: 5.9220. Min Act: -0.1700

Data Index: 3906127 (Open Web Text)

Max Activating Token Index: 8

Text #3

Max Range: 5.9665. Min Range: -5.9665

Max Act: 5.9163. Min Act: -0.1700

Data Index: 2618049 (Open Web Text)

Max Activating Token Index: 59

Text #4

Max Range: 5.9665. Min Range: -5.9665

Max Act: 5.9153. Min Act: -0.1700

Data Index: 7572242 (Open Web Text)

Max Activating Token Index: 75

Text #5

Max Range: 5.9665. Min Range: -5.9665

Max Act: 5.9001. Min Act: -0.1700

Data Index: 89950 (Open Web Text)

Max Activating Token Index: 9

Text #6

Max Range: 5.9665. Min Range: -5.9665

Max Act: 5.8725. Min Act: -0.1700

Data Index: 8514950 (Open Web Text)

Max Activating Token Index: 108

Text #7

Max Range: 5.9665. Min Range: -5.9665

Max Act: 5.8616. Min Act: -0.1700

Data Index: 3273675 (Open Web Text)

Max Activating Token Index: 7

Text #8

Max Range: 5.9665. Min Range: -5.9665

Max Act: 5.8984. Min Act: -0.1700

Data Index: 8092884 (Open Web Text)

Max Activating Token Index: 17

Text #9

Max Range: 5.9665. Min Range: -5.9665

Max Act: 5.8693. Min Act: -0.1700

Data Index: 2074224 (Open Web Text)

Max Activating Token Index: 419

Text #10

Max Range: 5.9665. Min Range: -5.9665

Max Act: 5.8582. Min Act: -0.1700

Data Index: 3990380 (Open Web Text)

Max Activating Token Index: 18

Text #11

Max Range: 5.9665. Min Range: -5.9665

Max Act: 5.8734. Min Act: -0.1700

Data Index: 8697815 (Open Web Text)

Max Activating Token Index: 24

Text #12

Max Range: 5.9665. Min Range: -5.9665

Max Act: 5.8779. Min Act: -0.1700

Data Index: 5324424 (Open Web Text)

Max Activating Token Index: 7

Text #13

Max Range: 5.9665. Min Range: -5.9665

Max Act: 5.8781. Min Act: -0.1700

Data Index: 1193027 (Open Web Text)

Max Activating Token Index: 20

Text #14

Max Range: 5.9665. Min Range: -5.9665

Max Act: 5.8832. Min Act: -0.1700

Data Index: 3157633 (Open Web Text)

Max Activating Token Index: 17

Text #15

Max Range: 5.9665. Min Range: -5.9665

Max Act: 5.8378. Min Act: -0.1700

Data Index: 356893 (Open Web Text)

Max Activating Token Index: 10

Text #16

Max Range: 5.9665. Min Range: -5.9665

Max Act: 5.8589. Min Act: -0.1700

Data Index: 2048561 (Open Web Text)

Max Activating Token Index: 16

Text #17

Max Range: 5.9665. Min Range: -5.9665

Max Act: 5.8537. Min Act: -0.1700

Data Index: 4923277 (Open Web Text)

Max Activating Token Index: 21

Text #18

Max Range: 5.9665. Min Range: -5.9665

Max Act: 5.8458. Min Act: -0.1700

Data Index: 276834 (Open Web Text)

Max Activating Token Index: 19

Text #19

Max Range: 5.9665. Min Range: -5.9665

Max Act: 5.8289. Min Act: -0.1700

Data Index: 729513 (Open Web Text)

Max Activating Token Index: 12