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

Dataset: Open Web Text

Neuron 132 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: 3.4710. Min Range: -3.4710

Max Act: 3.4710. Min Act: -0.1700

Data Index: 3948034 (Open Web Text)

Max Activating Token Index: 545

Text #1

Max Range: 3.4710. Min Range: -3.4710

Max Act: 3.4601. Min Act: -0.1700

Data Index: 5411205 (Open Web Text)

Max Activating Token Index: 600

Text #2

Max Range: 3.4710. Min Range: -3.4710

Max Act: 3.4394. Min Act: -0.1700

Data Index: 1756457 (Open Web Text)

Max Activating Token Index: 745

Text #3

Max Range: 3.4710. Min Range: -3.4710

Max Act: 3.4000. Min Act: -0.1700

Data Index: 937689 (Open Web Text)

Max Activating Token Index: 748

Text #4

Max Range: 3.4710. Min Range: -3.4710

Max Act: 3.3989. Min Act: -0.1700

Data Index: 1548849 (Open Web Text)

Max Activating Token Index: 532

Text #5

Max Range: 3.4710. Min Range: -3.4710

Max Act: 3.3817. Min Act: -0.1700

Data Index: 1118035 (Open Web Text)

Max Activating Token Index: 528

Text #6

Max Range: 3.4710. Min Range: -3.4710

Max Act: 3.3872. Min Act: -0.1700

Data Index: 5712585 (Open Web Text)

Max Activating Token Index: 636

Text #7

Max Range: 3.4710. Min Range: -3.4710

Max Act: 3.3639. Min Act: -0.1700

Data Index: 7099591 (Open Web Text)

Max Activating Token Index: 524

Text #8

Max Range: 3.4710. Min Range: -3.4710

Max Act: 3.3674. Min Act: -0.1700

Data Index: 4062885 (Open Web Text)

Max Activating Token Index: 824

Text #9

Max Range: 3.4710. Min Range: -3.4710

Max Act: 3.3688. Min Act: -0.1700

Data Index: 1526073 (Open Web Text)

Max Activating Token Index: 1017

Text #10

Max Range: 3.4710. Min Range: -3.4710

Max Act: 3.3500. Min Act: -0.1700

Data Index: 1752619 (Open Web Text)

Max Activating Token Index: 365

Text #11

Max Range: 3.4710. Min Range: -3.4710

Max Act: 3.3483. Min Act: -0.1700

Data Index: 5161626 (Open Web Text)

Max Activating Token Index: 761

Text #12

Max Range: 3.4710. Min Range: -3.4710

Max Act: 3.3416. Min Act: -0.1700

Data Index: 2892798 (Open Web Text)

Max Activating Token Index: 920

Text #13

Max Range: 3.4710. Min Range: -3.4710

Max Act: 3.3315. Min Act: -0.1700

Data Index: 2182511 (Open Web Text)

Max Activating Token Index: 308

Text #14

Max Range: 3.4710. Min Range: -3.4710

Max Act: 3.3154. Min Act: -0.1700

Data Index: 8513072 (Open Web Text)

Max Activating Token Index: 819

Text #15

Max Range: 3.4710. Min Range: -3.4710

Max Act: 3.3320. Min Act: -0.1700

Data Index: 7485015 (Open Web Text)

Max Activating Token Index: 266

Text #16

Max Range: 3.4710. Min Range: -3.4710

Max Act: 3.3271. Min Act: -0.1700

Data Index: 2940469 (Open Web Text)

Max Activating Token Index: 511

Text #17

Max Range: 3.4710. Min Range: -3.4710

Max Act: 3.3309. Min Act: -0.1700

Data Index: 7071517 (Open Web Text)

Max Activating Token Index: 321

Text #18

Max Range: 3.4710. Min Range: -3.4710

Max Act: 3.3259. Min Act: -0.1700

Data Index: 3226799 (Open Web Text)

Max Activating Token Index: 855

Text #19

Max Range: 3.4710. Min Range: -3.4710

Max Act: 3.3188. Min Act: -0.1700

Data Index: 3219429 (Open Web Text)

Max Activating Token Index: 954