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

Dataset: Open Web Text

Neuron 2141 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: 2.9471. Min Range: -2.9471

Max Act: 2.9471. Min Act: -0.1700

Data Index: 3656694 (Open Web Text)

Max Activating Token Index: 18

Text #1

Max Range: 2.9471. Min Range: -2.9471

Max Act: 2.7711. Min Act: -0.1700

Data Index: 7764673 (Open Web Text)

Max Activating Token Index: 4

Text #2

Max Range: 2.9471. Min Range: -2.9471

Max Act: 2.7819. Min Act: -0.1700

Data Index: 5378226 (Open Web Text)

Max Activating Token Index: 806

Text #3

Max Range: 2.9471. Min Range: -2.9471

Max Act: 2.7851. Min Act: -0.1700

Data Index: 1174648 (Open Web Text)

Max Activating Token Index: 13

Text #4

Max Range: 2.9471. Min Range: -2.9471

Max Act: 2.7804. Min Act: -0.1700

Data Index: 6320748 (Open Web Text)

Max Activating Token Index: 1000

Text #5

Max Range: 2.9471. Min Range: -2.9471

Max Act: 2.7550. Min Act: -0.1700

Data Index: 8118596 (Open Web Text)

Max Activating Token Index: 3

Text #6

Max Range: 2.9471. Min Range: -2.9471

Max Act: 2.7630. Min Act: -0.1700

Data Index: 4778765 (Open Web Text)

Max Activating Token Index: 4

Text #7

Max Range: 2.9471. Min Range: -2.9471

Max Act: 2.7661. Min Act: -0.1700

Data Index: 1996148 (Open Web Text)

Max Activating Token Index: 4

Text #8

Max Range: 2.9471. Min Range: -2.9471

Max Act: 2.7526. Min Act: -0.1700

Data Index: 4156919 (Open Web Text)

Max Activating Token Index: 12

Text #9

Max Range: 2.9471. Min Range: -2.9471

Max Act: 2.7528. Min Act: -0.1700

Data Index: 465444 (Open Web Text)

Max Activating Token Index: 560

Text #10

Max Range: 2.9471. Min Range: -2.9471

Max Act: 2.7652. Min Act: -0.1700

Data Index: 5508351 (Open Web Text)

Max Activating Token Index: 238

Text #11

Max Range: 2.9471. Min Range: -2.9471

Max Act: 2.7417. Min Act: -0.1700

Data Index: 812313 (Open Web Text)

Max Activating Token Index: 857

Text #12

Max Range: 2.9471. Min Range: -2.9471

Max Act: 2.7342. Min Act: -0.1700

Data Index: 5597116 (Open Web Text)

Max Activating Token Index: 6

Text #13

Max Range: 2.9471. Min Range: -2.9471

Max Act: 2.7071. Min Act: -0.1700

Data Index: 74056 (Open Web Text)

Max Activating Token Index: 433

Text #14

Max Range: 2.9471. Min Range: -2.9471

Max Act: 2.7122. Min Act: -0.1700

Data Index: 786815 (Open Web Text)

Max Activating Token Index: 301

Text #15

Max Range: 2.9471. Min Range: -2.9471

Max Act: 2.7096. Min Act: -0.1700

Data Index: 3733306 (Open Web Text)

Max Activating Token Index: 11

Text #16

Max Range: 2.9471. Min Range: -2.9471

Max Act: 2.7037. Min Act: -0.1700

Data Index: 468387 (Open Web Text)

Max Activating Token Index: 4

Text #17

Max Range: 2.9471. Min Range: -2.9471

Max Act: 2.7164. Min Act: -0.1700

Data Index: 5594210 (Open Web Text)

Max Activating Token Index: 5

Text #18

Max Range: 2.9471. Min Range: -2.9471

Max Act: 2.7189. Min Act: -0.1700

Data Index: 1241048 (Open Web Text)

Max Activating Token Index: 349

Text #19

Max Range: 2.9471. Min Range: -2.9471

Max Act: 2.7022. Min Act: -0.1700

Data Index: 4108490 (Open Web Text)

Max Activating Token Index: 459