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

Dataset: Open Web Text

Neuron 1737 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: 4.9541. Min Range: -4.9541

Max Act: 4.9541. Min Act: -0.1700

Data Index: 5900300 (Open Web Text)

Max Activating Token Index: 4

Text #1

Max Range: 4.9541. Min Range: -4.9541

Max Act: 4.8816. Min Act: -0.1700

Data Index: 2050627 (Open Web Text)

Max Activating Token Index: 5

Text #2

Max Range: 4.9541. Min Range: -4.9541

Max Act: 4.8827. Min Act: -0.1700

Data Index: 5021067 (Open Web Text)

Max Activating Token Index: 5

Text #3

Max Range: 4.9541. Min Range: -4.9541

Max Act: 4.8704. Min Act: -0.1700

Data Index: 683148 (Open Web Text)

Max Activating Token Index: 5

Text #4

Max Range: 4.9541. Min Range: -4.9541

Max Act: 4.8407. Min Act: -0.1700

Data Index: 4609432 (Open Web Text)

Max Activating Token Index: 4

Text #5

Max Range: 4.9541. Min Range: -4.9541

Max Act: 4.8467. Min Act: -0.1700

Data Index: 2590490 (Open Web Text)

Max Activating Token Index: 5

Text #6

Max Range: 4.9541. Min Range: -4.9541

Max Act: 4.8362. Min Act: -0.1700

Data Index: 6537283 (Open Web Text)

Max Activating Token Index: 5

Text #7

Max Range: 4.9541. Min Range: -4.9541

Max Act: 4.8503. Min Act: -0.1700

Data Index: 2085566 (Open Web Text)

Max Activating Token Index: 4

Text #8

Max Range: 4.9541. Min Range: -4.9541

Max Act: 4.8437. Min Act: -0.1700

Data Index: 3135390 (Open Web Text)

Max Activating Token Index: 4

Text #9

Max Range: 4.9541. Min Range: -4.9541

Max Act: 4.8227. Min Act: -0.1700

Data Index: 3134263 (Open Web Text)

Max Activating Token Index: 4

Text #10

Max Range: 4.9541. Min Range: -4.9541

Max Act: 4.7935. Min Act: -0.1700

Data Index: 3583715 (Open Web Text)

Max Activating Token Index: 5

Text #11

Max Range: 4.9541. Min Range: -4.9541

Max Act: 4.8053. Min Act: -0.1700

Data Index: 7092098 (Open Web Text)

Max Activating Token Index: 3

Text #12

Max Range: 4.9541. Min Range: -4.9541

Max Act: 4.8020. Min Act: -0.1700

Data Index: 7071079 (Open Web Text)

Max Activating Token Index: 4

Text #13

Max Range: 4.9541. Min Range: -4.9541

Max Act: 4.8059. Min Act: -0.1700

Data Index: 4547217 (Open Web Text)

Max Activating Token Index: 5

Text #14

Max Range: 4.9541. Min Range: -4.9541

Max Act: 4.7991. Min Act: -0.1700

Data Index: 5793201 (Open Web Text)

Max Activating Token Index: 5

Text #15

Max Range: 4.9541. Min Range: -4.9541

Max Act: 4.8263. Min Act: -0.1700

Data Index: 2649004 (Open Web Text)

Max Activating Token Index: 4

Text #16

Max Range: 4.9541. Min Range: -4.9541

Max Act: 4.8077. Min Act: -0.1700

Data Index: 5565438 (Open Web Text)

Max Activating Token Index: 5

Text #17

Max Range: 4.9541. Min Range: -4.9541

Max Act: 4.7855. Min Act: -0.1700

Data Index: 1541132 (Open Web Text)

Max Activating Token Index: 5

Text #18

Max Range: 4.9541. Min Range: -4.9541

Max Act: 4.7893. Min Act: -0.1700

Data Index: 3515695 (Open Web Text)

Max Activating Token Index: 9

Text #19

Max Range: 4.9541. Min Range: -4.9541

Max Act: 4.7671. Min Act: -0.1700

Data Index: 4212910 (Open Web Text)

Max Activating Token Index: 8