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

Dataset: Open Web Text

Neuron 437 in Layer 5

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: 4.4015. Min Range: -4.4015

Max Act: 4.4015. Min Act: -0.1700

Data Index: 8545128 (Open Web Text)

Max Activating Token Index: 388

Text #1

Max Range: 4.4015. Min Range: -4.4015

Max Act: 4.2787. Min Act: -0.1700

Data Index: 338234 (Open Web Text)

Max Activating Token Index: 425

Text #2

Max Range: 4.4015. Min Range: -4.4015

Max Act: 4.2853. Min Act: -0.1700

Data Index: 859650 (Open Web Text)

Max Activating Token Index: 87

Text #3

Max Range: 4.4015. Min Range: -4.4015

Max Act: 4.2169. Min Act: -0.1700

Data Index: 7692772 (Open Web Text)

Max Activating Token Index: 883

Text #4

Max Range: 4.4015. Min Range: -4.4015

Max Act: 4.2167. Min Act: -0.1700

Data Index: 8594963 (Open Web Text)

Max Activating Token Index: 986

Text #5

Max Range: 4.4015. Min Range: -4.4015

Max Act: 4.1846. Min Act: -0.1700

Data Index: 2070531 (Open Web Text)

Max Activating Token Index: 979

Text #6

Max Range: 4.4015. Min Range: -4.4015

Max Act: 4.1643. Min Act: -0.1700

Data Index: 6377768 (Open Web Text)

Max Activating Token Index: 549

Text #7

Max Range: 4.4015. Min Range: -4.4015

Max Act: 4.1822. Min Act: -0.1700

Data Index: 3970278 (Open Web Text)

Max Activating Token Index: 666

Text #8

Max Range: 4.4015. Min Range: -4.4015

Max Act: 4.1445. Min Act: -0.1700

Data Index: 8426566 (Open Web Text)

Max Activating Token Index: 925

Text #9

Max Range: 4.4015. Min Range: -4.4015

Max Act: 4.1678. Min Act: -0.1700

Data Index: 4731083 (Open Web Text)

Max Activating Token Index: 50

Text #10

Max Range: 4.4015. Min Range: -4.4015

Max Act: 4.1486. Min Act: -0.1700

Data Index: 8357582 (Open Web Text)

Max Activating Token Index: 775

Text #11

Max Range: 4.4015. Min Range: -4.4015

Max Act: 4.1291. Min Act: -0.1700

Data Index: 2779294 (Open Web Text)

Max Activating Token Index: 844

Text #12

Max Range: 4.4015. Min Range: -4.4015

Max Act: 4.1178. Min Act: -0.1700

Data Index: 4759195 (Open Web Text)

Max Activating Token Index: 982

Text #13

Max Range: 4.4015. Min Range: -4.4015

Max Act: 4.1152. Min Act: -0.1700

Data Index: 6105877 (Open Web Text)

Max Activating Token Index: 115

Text #14

Max Range: 4.4015. Min Range: -4.4015

Max Act: 4.1356. Min Act: -0.1700

Data Index: 6621025 (Open Web Text)

Max Activating Token Index: 207

Text #15

Max Range: 4.4015. Min Range: -4.4015

Max Act: 4.1408. Min Act: -0.1700

Data Index: 5578266 (Open Web Text)

Max Activating Token Index: 78

Text #16

Max Range: 4.4015. Min Range: -4.4015

Max Act: 4.0843. Min Act: -0.1700

Data Index: 4126785 (Open Web Text)

Max Activating Token Index: 157

Text #17

Max Range: 4.4015. Min Range: -4.4015

Max Act: 4.1017. Min Act: -0.1700

Data Index: 7200716 (Open Web Text)

Max Activating Token Index: 774

Text #18

Max Range: 4.4015. Min Range: -4.4015

Max Act: 4.1041. Min Act: -0.1700

Data Index: 6282534 (Open Web Text)

Max Activating Token Index: 144

Text #19

Max Range: 4.4015. Min Range: -4.4015

Max Act: 4.0681. Min Act: -0.1700

Data Index: 5459716 (Open Web Text)

Max Activating Token Index: 72