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

Dataset: Open Web Text

Neuron 1547 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: 3.5386. Min Range: -3.5386

Max Act: 3.5386. Min Act: -0.1700

Data Index: 8350373 (Open Web Text)

Max Activating Token Index: 2

Text #1

Max Range: 3.5386. Min Range: -3.5386

Max Act: 3.5386. Min Act: -0.1700

Data Index: 2149681 (Open Web Text)

Max Activating Token Index: 2

Text #2

Max Range: 3.5386. Min Range: -3.5386

Max Act: 3.5114. Min Act: -0.1700

Data Index: 4411940 (Open Web Text)

Max Activating Token Index: 3

Text #3

Max Range: 3.5386. Min Range: -3.5386

Max Act: 3.4892. Min Act: -0.1700

Data Index: 1895997 (Open Web Text)

Max Activating Token Index: 5

Text #4

Max Range: 3.5386. Min Range: -3.5386

Max Act: 3.5017. Min Act: -0.1700

Data Index: 2861279 (Open Web Text)

Max Activating Token Index: 5

Text #5

Max Range: 3.5386. Min Range: -3.5386

Max Act: 3.4920. Min Act: -0.1700

Data Index: 628114 (Open Web Text)

Max Activating Token Index: 4

Text #6

Max Range: 3.5386. Min Range: -3.5386

Max Act: 3.4920. Min Act: -0.1700

Data Index: 8726313 (Open Web Text)

Max Activating Token Index: 4

Text #7

Max Range: 3.5386. Min Range: -3.5386

Max Act: 3.4961. Min Act: -0.1700

Data Index: 8440624 (Open Web Text)

Max Activating Token Index: 3

Text #8

Max Range: 3.5386. Min Range: -3.5386

Max Act: 3.4830. Min Act: -0.1700

Data Index: 123421 (Open Web Text)

Max Activating Token Index: 5

Text #9

Max Range: 3.5386. Min Range: -3.5386

Max Act: 3.4635. Min Act: -0.1700

Data Index: 1366238 (Open Web Text)

Max Activating Token Index: 6

Text #10

Max Range: 3.5386. Min Range: -3.5386

Max Act: 3.4673. Min Act: -0.1700

Data Index: 6327765 (Open Web Text)

Max Activating Token Index: 3

Text #11

Max Range: 3.5386. Min Range: -3.5386

Max Act: 3.4432. Min Act: -0.1700

Data Index: 6706827 (Open Web Text)

Max Activating Token Index: 5

Text #12

Max Range: 3.5386. Min Range: -3.5386

Max Act: 3.4455. Min Act: -0.1700

Data Index: 3028276 (Open Web Text)

Max Activating Token Index: 4

Text #13

Max Range: 3.5386. Min Range: -3.5386

Max Act: 3.4431. Min Act: -0.1700

Data Index: 7473426 (Open Web Text)

Max Activating Token Index: 2

Text #14

Max Range: 3.5386. Min Range: -3.5386

Max Act: 3.4310. Min Act: -0.1700

Data Index: 6264145 (Open Web Text)

Max Activating Token Index: 4

Text #15

Max Range: 3.5386. Min Range: -3.5386

Max Act: 3.4236. Min Act: -0.1700

Data Index: 3864766 (Open Web Text)

Max Activating Token Index: 7

Text #16

Max Range: 3.5386. Min Range: -3.5386

Max Act: 3.4266. Min Act: -0.1700

Data Index: 512706 (Open Web Text)

Max Activating Token Index: 5

Text #17

Max Range: 3.5386. Min Range: -3.5386

Max Act: 3.4292. Min Act: -0.1700

Data Index: 5380728 (Open Web Text)

Max Activating Token Index: 4

Text #18

Max Range: 3.5386. Min Range: -3.5386

Max Act: 3.4210. Min Act: -0.1700

Data Index: 3488724 (Open Web Text)

Max Activating Token Index: 6

Text #19

Max Range: 3.5386. Min Range: -3.5386

Max Act: 3.4217. Min Act: -0.1700

Data Index: 6294880 (Open Web Text)

Max Activating Token Index: 8