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

Dataset: Open Web Text

Neuron 2799 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: 4.1218. Min Range: -4.1218

Max Act: 4.1218. Min Act: -0.1700

Data Index: 8580927 (Open Web Text)

Max Activating Token Index: 7

Text #1

Max Range: 4.1218. Min Range: -4.1218

Max Act: 4.0316. Min Act: -0.1700

Data Index: 4093768 (Open Web Text)

Max Activating Token Index: 7

Text #2

Max Range: 4.1218. Min Range: -4.1218

Max Act: 3.9826. Min Act: -0.1700

Data Index: 4309327 (Open Web Text)

Max Activating Token Index: 9

Text #3

Max Range: 4.1218. Min Range: -4.1218

Max Act: 3.9706. Min Act: -0.1700

Data Index: 6654996 (Open Web Text)

Max Activating Token Index: 5

Text #4

Max Range: 4.1218. Min Range: -4.1218

Max Act: 3.9411. Min Act: -0.1700

Data Index: 2340999 (Open Web Text)

Max Activating Token Index: 986

Text #5

Max Range: 4.1218. Min Range: -4.1218

Max Act: 3.9187. Min Act: -0.1700

Data Index: 6534541 (Open Web Text)

Max Activating Token Index: 15

Text #6

Max Range: 4.1218. Min Range: -4.1218

Max Act: 3.9089. Min Act: -0.1700

Data Index: 8340444 (Open Web Text)

Max Activating Token Index: 7

Text #7

Max Range: 4.1218. Min Range: -4.1218

Max Act: 3.9385. Min Act: -0.1700

Data Index: 2206280 (Open Web Text)

Max Activating Token Index: 32

Text #8

Max Range: 4.1218. Min Range: -4.1218

Max Act: 3.9226. Min Act: -0.1700

Data Index: 629281 (Open Web Text)

Max Activating Token Index: 9

Text #9

Max Range: 4.1218. Min Range: -4.1218

Max Act: 3.8799. Min Act: -0.1700

Data Index: 370215 (Open Web Text)

Max Activating Token Index: 247

Text #10

Max Range: 4.1218. Min Range: -4.1218

Max Act: 3.9083. Min Act: -0.1700

Data Index: 4664160 (Open Web Text)

Max Activating Token Index: 9

Text #11

Max Range: 4.1218. Min Range: -4.1218

Max Act: 3.8786. Min Act: -0.1700

Data Index: 2281133 (Open Web Text)

Max Activating Token Index: 793

Text #12

Max Range: 4.1218. Min Range: -4.1218

Max Act: 3.8935. Min Act: -0.1700

Data Index: 2070458 (Open Web Text)

Max Activating Token Index: 42

Text #13

Max Range: 4.1218. Min Range: -4.1218

Max Act: 3.8819. Min Act: -0.1700

Data Index: 3722701 (Open Web Text)

Max Activating Token Index: 500

Text #14

Max Range: 4.1218. Min Range: -4.1218

Max Act: 3.8843. Min Act: -0.1700

Data Index: 1218844 (Open Web Text)

Max Activating Token Index: 123

Text #15

Max Range: 4.1218. Min Range: -4.1218

Max Act: 3.8905. Min Act: -0.1700

Data Index: 7594289 (Open Web Text)

Max Activating Token Index: 9

Text #16

Max Range: 4.1218. Min Range: -4.1218

Max Act: 3.9095. Min Act: -0.1700

Data Index: 6506124 (Open Web Text)

Max Activating Token Index: 16

Text #17

Max Range: 4.1218. Min Range: -4.1218

Max Act: 3.9083. Min Act: -0.1700

Data Index: 1467829 (Open Web Text)

Max Activating Token Index: 23

Text #18

Max Range: 4.1218. Min Range: -4.1218

Max Act: 3.8905. Min Act: -0.1700

Data Index: 4918511 (Open Web Text)

Max Activating Token Index: 718

Text #19

Max Range: 4.1218. Min Range: -4.1218

Max Act: 3.8621. Min Act: -0.1700

Data Index: 4665190 (Open Web Text)

Max Activating Token Index: 33