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

Dataset: Open Web Text

Neuron 1830 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: 3.6255. Min Range: -3.6255

Max Act: 3.6255. Min Act: -0.1700

Data Index: 4305944 (Open Web Text)

Max Activating Token Index: 3

Text #1

Max Range: 3.6255. Min Range: -3.6255

Max Act: 3.5655. Min Act: -0.1700

Data Index: 2365636 (Open Web Text)

Max Activating Token Index: 3

Text #2

Max Range: 3.6255. Min Range: -3.6255

Max Act: 3.5479. Min Act: -0.1700

Data Index: 4056147 (Open Web Text)

Max Activating Token Index: 3

Text #3

Max Range: 3.6255. Min Range: -3.6255

Max Act: 3.5623. Min Act: -0.1700

Data Index: 6384200 (Open Web Text)

Max Activating Token Index: 5

Text #4

Max Range: 3.6255. Min Range: -3.6255

Max Act: 3.5322. Min Act: -0.1700

Data Index: 2363394 (Open Web Text)

Max Activating Token Index: 3

Text #5

Max Range: 3.6255. Min Range: -3.6255

Max Act: 3.5221. Min Act: -0.1700

Data Index: 5822829 (Open Web Text)

Max Activating Token Index: 5

Text #6

Max Range: 3.6255. Min Range: -3.6255

Max Act: 3.5181. Min Act: -0.1700

Data Index: 2534454 (Open Web Text)

Max Activating Token Index: 3

Text #7

Max Range: 3.6255. Min Range: -3.6255

Max Act: 3.5181. Min Act: -0.1700

Data Index: 5619981 (Open Web Text)

Max Activating Token Index: 8

Text #8

Max Range: 3.6255. Min Range: -3.6255

Max Act: 3.5072. Min Act: -0.1700

Data Index: 5748060 (Open Web Text)

Max Activating Token Index: 2

Text #9

Max Range: 3.6255. Min Range: -3.6255

Max Act: 3.4946. Min Act: -0.1700

Data Index: 7042583 (Open Web Text)

Max Activating Token Index: 5

Text #10

Max Range: 3.6255. Min Range: -3.6255

Max Act: 3.4810. Min Act: -0.1700

Data Index: 4864128 (Open Web Text)

Max Activating Token Index: 3

Text #11

Max Range: 3.6255. Min Range: -3.6255

Max Act: 3.4944. Min Act: -0.1700

Data Index: 5097389 (Open Web Text)

Max Activating Token Index: 5

Text #12

Max Range: 3.6255. Min Range: -3.6255

Max Act: 3.4875. Min Act: -0.1700

Data Index: 103996 (Open Web Text)

Max Activating Token Index: 4

Text #13

Max Range: 3.6255. Min Range: -3.6255

Max Act: 3.5140. Min Act: -0.1700

Data Index: 2072896 (Open Web Text)

Max Activating Token Index: 4

Text #14

Max Range: 3.6255. Min Range: -3.6255

Max Act: 3.4984. Min Act: -0.1700

Data Index: 2975814 (Open Web Text)

Max Activating Token Index: 3

Text #15

Max Range: 3.6255. Min Range: -3.6255

Max Act: 3.4646. Min Act: -0.1700

Data Index: 5072486 (Open Web Text)

Max Activating Token Index: 4

Text #16

Max Range: 3.6255. Min Range: -3.6255

Max Act: 3.4517. Min Act: -0.1700

Data Index: 4420040 (Open Web Text)

Max Activating Token Index: 3

Text #17

Max Range: 3.6255. Min Range: -3.6255

Max Act: 3.4582. Min Act: -0.1700

Data Index: 4427097 (Open Web Text)

Max Activating Token Index: 3

Text #18

Max Range: 3.6255. Min Range: -3.6255

Max Act: 3.4646. Min Act: -0.1700

Data Index: 1572331 (Open Web Text)

Max Activating Token Index: 3

Text #19

Max Range: 3.6255. Min Range: -3.6255

Max Act: 3.4719. Min Act: -0.1700

Data Index: 5535877 (Open Web Text)

Max Activating Token Index: 4