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

Dataset: Open Web Text

Neuron 2356 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: 3.8586. Min Range: -3.8586

Max Act: 3.8586. Min Act: -0.1700

Data Index: 1942147 (Open Web Text)

Max Activating Token Index: 5

Text #1

Max Range: 3.8586. Min Range: -3.8586

Max Act: 3.7963. Min Act: -0.1700

Data Index: 558862 (Open Web Text)

Max Activating Token Index: 6

Text #2

Max Range: 3.8586. Min Range: -3.8586

Max Act: 3.7985. Min Act: -0.1700

Data Index: 4796220 (Open Web Text)

Max Activating Token Index: 7

Text #3

Max Range: 3.8586. Min Range: -3.8586

Max Act: 3.7737. Min Act: -0.1700

Data Index: 3718741 (Open Web Text)

Max Activating Token Index: 4

Text #4

Max Range: 3.8586. Min Range: -3.8586

Max Act: 3.7683. Min Act: -0.1700

Data Index: 5346095 (Open Web Text)

Max Activating Token Index: 2

Text #5

Max Range: 3.8586. Min Range: -3.8586

Max Act: 3.7551. Min Act: -0.1700

Data Index: 2463881 (Open Web Text)

Max Activating Token Index: 5

Text #6

Max Range: 3.8586. Min Range: -3.8586

Max Act: 3.7606. Min Act: -0.1700

Data Index: 646302 (Open Web Text)

Max Activating Token Index: 4

Text #7

Max Range: 3.8586. Min Range: -3.8586

Max Act: 3.7582. Min Act: -0.1700

Data Index: 6982712 (Open Web Text)

Max Activating Token Index: 3

Text #8

Max Range: 3.8586. Min Range: -3.8586

Max Act: 3.7356. Min Act: -0.1700

Data Index: 4611989 (Open Web Text)

Max Activating Token Index: 6

Text #9

Max Range: 3.8586. Min Range: -3.8586

Max Act: 3.7340. Min Act: -0.1700

Data Index: 2361758 (Open Web Text)

Max Activating Token Index: 7

Text #10

Max Range: 3.8586. Min Range: -3.8586

Max Act: 3.7333. Min Act: -0.1700

Data Index: 1394475 (Open Web Text)

Max Activating Token Index: 5

Text #11

Max Range: 3.8586. Min Range: -3.8586

Max Act: 3.7410. Min Act: -0.1700

Data Index: 1556529 (Open Web Text)

Max Activating Token Index: 3

Text #12

Max Range: 3.8586. Min Range: -3.8586

Max Act: 3.7172. Min Act: -0.1700

Data Index: 4509956 (Open Web Text)

Max Activating Token Index: 10

Text #13

Max Range: 3.8586. Min Range: -3.8586

Max Act: 3.7379. Min Act: -0.1700

Data Index: 5041277 (Open Web Text)

Max Activating Token Index: 8

Text #14

Max Range: 3.8586. Min Range: -3.8586

Max Act: 3.7256. Min Act: -0.1700

Data Index: 3423074 (Open Web Text)

Max Activating Token Index: 5

Text #15

Max Range: 3.8586. Min Range: -3.8586

Max Act: 3.7332. Min Act: -0.1700

Data Index: 2638847 (Open Web Text)

Max Activating Token Index: 2

Text #16

Max Range: 3.8586. Min Range: -3.8586

Max Act: 3.7238. Min Act: -0.1700

Data Index: 2670021 (Open Web Text)

Max Activating Token Index: 4

Text #17

Max Range: 3.8586. Min Range: -3.8586

Max Act: 3.7462. Min Act: -0.1700

Data Index: 2684372 (Open Web Text)

Max Activating Token Index: 6

Text #18

Max Range: 3.8586. Min Range: -3.8586

Max Act: 3.7332. Min Act: -0.1700

Data Index: 2772650 (Open Web Text)

Max Activating Token Index: 2

Text #19

Max Range: 3.8586. Min Range: -3.8586

Max Act: 3.7263. Min Act: -0.1700

Data Index: 6633836 (Open Web Text)

Max Activating Token Index: 18