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

Dataset: Open Web Text

Neuron 2650 in Layer 2

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: 3.7031. Min Range: -3.7031

Max Act: 3.7031. Min Act: -0.1700

Data Index: 1313795 (Open Web Text)

Max Activating Token Index: 117

Text #1

Max Range: 3.7031. Min Range: -3.7031

Max Act: 3.6694. Min Act: -0.1700

Data Index: 255840 (Open Web Text)

Max Activating Token Index: 767

Text #2

Max Range: 3.7031. Min Range: -3.7031

Max Act: 3.5594. Min Act: -0.1700

Data Index: 4833872 (Open Web Text)

Max Activating Token Index: 723

Text #3

Max Range: 3.7031. Min Range: -3.7031

Max Act: 3.5719. Min Act: -0.1700

Data Index: 3363554 (Open Web Text)

Max Activating Token Index: 557

Text #4

Max Range: 3.7031. Min Range: -3.7031

Max Act: 3.5571. Min Act: -0.1700

Data Index: 255827 (Open Web Text)

Max Activating Token Index: 296

Text #5

Max Range: 3.7031. Min Range: -3.7031

Max Act: 3.5362. Min Act: -0.1700

Data Index: 79120 (Open Web Text)

Max Activating Token Index: 916

Text #6

Max Range: 3.7031. Min Range: -3.7031

Max Act: 3.5078. Min Act: -0.1700

Data Index: 1335200 (Open Web Text)

Max Activating Token Index: 279

Text #7

Max Range: 3.7031. Min Range: -3.7031

Max Act: 3.4752. Min Act: -0.1700

Data Index: 255843 (Open Web Text)

Max Activating Token Index: 412

Text #8

Max Range: 3.7031. Min Range: -3.7031

Max Act: 3.4694. Min Act: -0.1700

Data Index: 687519 (Open Web Text)

Max Activating Token Index: 422

Text #9

Max Range: 3.7031. Min Range: -3.7031

Max Act: 3.4545. Min Act: -0.1700

Data Index: 6757254 (Open Web Text)

Max Activating Token Index: 485

Text #10

Max Range: 3.7031. Min Range: -3.7031

Max Act: 3.4505. Min Act: -0.1700

Data Index: 1827733 (Open Web Text)

Max Activating Token Index: 355

Text #11

Max Range: 3.7031. Min Range: -3.7031

Max Act: 3.4525. Min Act: -0.1700

Data Index: 5475199 (Open Web Text)

Max Activating Token Index: 125

Text #12

Max Range: 3.7031. Min Range: -3.7031

Max Act: 3.4495. Min Act: -0.1700

Data Index: 378066 (Open Web Text)

Max Activating Token Index: 605

Text #13

Max Range: 3.7031. Min Range: -3.7031

Max Act: 3.4259. Min Act: -0.1700

Data Index: 7237274 (Open Web Text)

Max Activating Token Index: 405

Text #14

Max Range: 3.7031. Min Range: -3.7031

Max Act: 3.4255. Min Act: -0.1700

Data Index: 2419357 (Open Web Text)

Max Activating Token Index: 911

Text #15

Max Range: 3.7031. Min Range: -3.7031

Max Act: 3.3968. Min Act: -0.1700

Data Index: 6008783 (Open Web Text)

Max Activating Token Index: 99

Text #16

Max Range: 3.7031. Min Range: -3.7031

Max Act: 3.4023. Min Act: -0.1700

Data Index: 3504861 (Open Web Text)

Max Activating Token Index: 344

Text #17

Max Range: 3.7031. Min Range: -3.7031

Max Act: 3.3812. Min Act: -0.1700

Data Index: 6008782 (Open Web Text)

Max Activating Token Index: 190

Text #18

Max Range: 3.7031. Min Range: -3.7031

Max Act: 3.3717. Min Act: -0.1700

Data Index: 1313796 (Open Web Text)

Max Activating Token Index: 852

Text #19

Max Range: 3.7031. Min Range: -3.7031

Max Act: 3.3948. Min Act: -0.1700

Data Index: 3991411 (Open Web Text)

Max Activating Token Index: 125