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

Dataset: Open Web Text

Neuron 2568 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: 5.5598. Min Range: -5.5598

Max Act: 5.5598. Min Act: -0.1700

Data Index: 2368424 (Open Web Text)

Max Activating Token Index: 4

Text #1

Max Range: 5.5598. Min Range: -5.5598

Max Act: 5.4517. Min Act: -0.1700

Data Index: 1990264 (Open Web Text)

Max Activating Token Index: 4

Text #2

Max Range: 5.5598. Min Range: -5.5598

Max Act: 5.4552. Min Act: -0.1700

Data Index: 2351514 (Open Web Text)

Max Activating Token Index: 987

Text #3

Max Range: 5.5598. Min Range: -5.5598

Max Act: 5.4201. Min Act: -0.1700

Data Index: 3178056 (Open Web Text)

Max Activating Token Index: 6

Text #4

Max Range: 5.5598. Min Range: -5.5598

Max Act: 5.4277. Min Act: -0.1700

Data Index: 3984852 (Open Web Text)

Max Activating Token Index: 5

Text #5

Max Range: 5.5598. Min Range: -5.5598

Max Act: 5.4136. Min Act: -0.1700

Data Index: 6476545 (Open Web Text)

Max Activating Token Index: 5

Text #6

Max Range: 5.5598. Min Range: -5.5598

Max Act: 5.3898. Min Act: -0.1700

Data Index: 7220166 (Open Web Text)

Max Activating Token Index: 1019

Text #7

Max Range: 5.5598. Min Range: -5.5598

Max Act: 5.3679. Min Act: -0.1700

Data Index: 1298523 (Open Web Text)

Max Activating Token Index: 5

Text #8

Max Range: 5.5598. Min Range: -5.5598

Max Act: 5.3788. Min Act: -0.1700

Data Index: 5955821 (Open Web Text)

Max Activating Token Index: 5

Text #9

Max Range: 5.5598. Min Range: -5.5598

Max Act: 5.3845. Min Act: -0.1700

Data Index: 1144403 (Open Web Text)

Max Activating Token Index: 3

Text #10

Max Range: 5.5598. Min Range: -5.5598

Max Act: 5.3539. Min Act: -0.1700

Data Index: 4752810 (Open Web Text)

Max Activating Token Index: 533

Text #11

Max Range: 5.5598. Min Range: -5.5598

Max Act: 5.3555. Min Act: -0.1700

Data Index: 4591126 (Open Web Text)

Max Activating Token Index: 7

Text #12

Max Range: 5.5598. Min Range: -5.5598

Max Act: 5.3671. Min Act: -0.1700

Data Index: 6480157 (Open Web Text)

Max Activating Token Index: 5

Text #13

Max Range: 5.5598. Min Range: -5.5598

Max Act: 5.3412. Min Act: -0.1700

Data Index: 396233 (Open Web Text)

Max Activating Token Index: 6

Text #14

Max Range: 5.5598. Min Range: -5.5598

Max Act: 5.3523. Min Act: -0.1700

Data Index: 6453655 (Open Web Text)

Max Activating Token Index: 5

Text #15

Max Range: 5.5598. Min Range: -5.5598

Max Act: 5.3500. Min Act: -0.1700

Data Index: 1008618 (Open Web Text)

Max Activating Token Index: 7

Text #16

Max Range: 5.5598. Min Range: -5.5598

Max Act: 5.3641. Min Act: -0.1700

Data Index: 5775085 (Open Web Text)

Max Activating Token Index: 7

Text #17

Max Range: 5.5598. Min Range: -5.5598

Max Act: 5.3605. Min Act: -0.1700

Data Index: 3292385 (Open Web Text)

Max Activating Token Index: 8

Text #18

Max Range: 5.5598. Min Range: -5.5598

Max Act: 5.3502. Min Act: -0.1700

Data Index: 5125153 (Open Web Text)

Max Activating Token Index: 4

Text #19

Max Range: 5.5598. Min Range: -5.5598

Max Act: 5.3599. Min Act: -0.1700

Data Index: 3134459 (Open Web Text)

Max Activating Token Index: 5