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

Dataset: Open Web Text

Neuron 2216 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: 2.8237. Min Range: -2.8237

Max Act: 2.8237. Min Act: -0.1700

Data Index: 581345 (Open Web Text)

Max Activating Token Index: 4

Text #1

Max Range: 2.8237. Min Range: -2.8237

Max Act: 2.7875. Min Act: -0.1700

Data Index: 5204445 (Open Web Text)

Max Activating Token Index: 3

Text #2

Max Range: 2.8237. Min Range: -2.8237

Max Act: 2.7214. Min Act: -0.1700

Data Index: 910151 (Open Web Text)

Max Activating Token Index: 18

Text #3

Max Range: 2.8237. Min Range: -2.8237

Max Act: 2.7021. Min Act: -0.1700

Data Index: 8784339 (Open Web Text)

Max Activating Token Index: 17

Text #4

Max Range: 2.8237. Min Range: -2.8237

Max Act: 2.6814. Min Act: -0.1700

Data Index: 866208 (Open Web Text)

Max Activating Token Index: 2

Text #5

Max Range: 2.8237. Min Range: -2.8237

Max Act: 2.6768. Min Act: -0.1700

Data Index: 1209674 (Open Web Text)

Max Activating Token Index: 15

Text #6

Max Range: 2.8237. Min Range: -2.8237

Max Act: 2.6624. Min Act: -0.1700

Data Index: 3034364 (Open Web Text)

Max Activating Token Index: 8

Text #7

Max Range: 2.8237. Min Range: -2.8237

Max Act: 2.6661. Min Act: -0.1700

Data Index: 8759086 (Open Web Text)

Max Activating Token Index: 3

Text #8

Max Range: 2.8237. Min Range: -2.8237

Max Act: 2.6709. Min Act: -0.1700

Data Index: 4893840 (Open Web Text)

Max Activating Token Index: 7

Text #9

Max Range: 2.8237. Min Range: -2.8237

Max Act: 2.6622. Min Act: -0.1700

Data Index: 8531095 (Open Web Text)

Max Activating Token Index: 16

Text #10

Max Range: 2.8237. Min Range: -2.8237

Max Act: 2.6349. Min Act: -0.1700

Data Index: 4507729 (Open Web Text)

Max Activating Token Index: 2

Text #11

Max Range: 2.8237. Min Range: -2.8237

Max Act: 2.6317. Min Act: -0.1700

Data Index: 792870 (Open Web Text)

Max Activating Token Index: 6

Text #12

Max Range: 2.8237. Min Range: -2.8237

Max Act: 2.6307. Min Act: -0.1700

Data Index: 2953480 (Open Web Text)

Max Activating Token Index: 5

Text #13

Max Range: 2.8237. Min Range: -2.8237

Max Act: 2.6430. Min Act: -0.1700

Data Index: 6620511 (Open Web Text)

Max Activating Token Index: 8

Text #14

Max Range: 2.8237. Min Range: -2.8237

Max Act: 2.6407. Min Act: -0.1700

Data Index: 7927056 (Open Web Text)

Max Activating Token Index: 11

Text #15

Max Range: 2.8237. Min Range: -2.8237

Max Act: 2.6143. Min Act: -0.1700

Data Index: 6743943 (Open Web Text)

Max Activating Token Index: 3

Text #16

Max Range: 2.8237. Min Range: -2.8237

Max Act: 2.6260. Min Act: -0.1700

Data Index: 790525 (Open Web Text)

Max Activating Token Index: 6

Text #17

Max Range: 2.8237. Min Range: -2.8237

Max Act: 2.6164. Min Act: -0.1700

Data Index: 7089951 (Open Web Text)

Max Activating Token Index: 958

Text #18

Max Range: 2.8237. Min Range: -2.8237

Max Act: 2.6264. Min Act: -0.1700

Data Index: 5717407 (Open Web Text)

Max Activating Token Index: 4

Text #19

Max Range: 2.8237. Min Range: -2.8237

Max Act: 2.6248. Min Act: -0.1700

Data Index: 3888664 (Open Web Text)

Max Activating Token Index: 9