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

Dataset: Open Web Text

Neuron 1433 in Layer 6

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: 3.6094. Min Range: -3.6094

Max Act: 3.6094. Min Act: -0.1700

Data Index: 3660892 (Open Web Text)

Max Activating Token Index: 336

Text #1

Max Range: 3.6094. Min Range: -3.6094

Max Act: 3.5522. Min Act: -0.1700

Data Index: 8323303 (Open Web Text)

Max Activating Token Index: 865

Text #2

Max Range: 3.6094. Min Range: -3.6094

Max Act: 3.5444. Min Act: -0.1700

Data Index: 6031954 (Open Web Text)

Max Activating Token Index: 696

Text #3

Max Range: 3.6094. Min Range: -3.6094

Max Act: 3.5263. Min Act: -0.1700

Data Index: 927860 (Open Web Text)

Max Activating Token Index: 823

Text #4

Max Range: 3.6094. Min Range: -3.6094

Max Act: 3.4917. Min Act: -0.1700

Data Index: 6144243 (Open Web Text)

Max Activating Token Index: 416

Text #5

Max Range: 3.6094. Min Range: -3.6094

Max Act: 3.4929. Min Act: -0.1700

Data Index: 8243747 (Open Web Text)

Max Activating Token Index: 886

Text #6

Max Range: 3.6094. Min Range: -3.6094

Max Act: 3.4775. Min Act: -0.1700

Data Index: 5378394 (Open Web Text)

Max Activating Token Index: 517

Text #7

Max Range: 3.6094. Min Range: -3.6094

Max Act: 3.4588. Min Act: -0.1700

Data Index: 5872466 (Open Web Text)

Max Activating Token Index: 549

Text #8

Max Range: 3.6094. Min Range: -3.6094

Max Act: 3.4447. Min Act: -0.1700

Data Index: 6173130 (Open Web Text)

Max Activating Token Index: 498

Text #9

Max Range: 3.6094. Min Range: -3.6094

Max Act: 3.4231. Min Act: -0.1700

Data Index: 3661748 (Open Web Text)

Max Activating Token Index: 519

Text #10

Max Range: 3.6094. Min Range: -3.6094

Max Act: 3.4464. Min Act: -0.1700

Data Index: 5408409 (Open Web Text)

Max Activating Token Index: 926

Text #11

Max Range: 3.6094. Min Range: -3.6094

Max Act: 3.4146. Min Act: -0.1700

Data Index: 4932072 (Open Web Text)

Max Activating Token Index: 938

Text #12

Max Range: 3.6094. Min Range: -3.6094

Max Act: 3.4290. Min Act: -0.1700

Data Index: 7189925 (Open Web Text)

Max Activating Token Index: 405

Text #13

Max Range: 3.6094. Min Range: -3.6094

Max Act: 3.4308. Min Act: -0.1700

Data Index: 8522348 (Open Web Text)

Max Activating Token Index: 429

Text #14

Max Range: 3.6094. Min Range: -3.6094

Max Act: 3.4139. Min Act: -0.1700

Data Index: 1612989 (Open Web Text)

Max Activating Token Index: 965

Text #15

Max Range: 3.6094. Min Range: -3.6094

Max Act: 3.4069. Min Act: -0.1700

Data Index: 2936463 (Open Web Text)

Max Activating Token Index: 625

Text #16

Max Range: 3.6094. Min Range: -3.6094

Max Act: 3.4020. Min Act: -0.1700

Data Index: 7111803 (Open Web Text)

Max Activating Token Index: 502

Text #17

Max Range: 3.6094. Min Range: -3.6094

Max Act: 3.4014. Min Act: -0.1700

Data Index: 8319609 (Open Web Text)

Max Activating Token Index: 346

Text #18

Max Range: 3.6094. Min Range: -3.6094

Max Act: 3.4070. Min Act: -0.1700

Data Index: 8127701 (Open Web Text)

Max Activating Token Index: 558

Text #19

Max Range: 3.6094. Min Range: -3.6094

Max Act: 3.4115. Min Act: -0.1700

Data Index: 7872209 (Open Web Text)

Max Activating Token Index: 671