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

Dataset: Open Web Text

Neuron 1102 in Layer 4

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: 4.7602. Min Range: -4.7602

Max Act: 4.7602. Min Act: -0.1700

Data Index: 960860 (Open Web Text)

Max Activating Token Index: 158

Text #1

Max Range: 4.7602. Min Range: -4.7602

Max Act: 4.7123. Min Act: -0.1700

Data Index: 2773568 (Open Web Text)

Max Activating Token Index: 987

Text #2

Max Range: 4.7602. Min Range: -4.7602

Max Act: 4.6379. Min Act: -0.1700

Data Index: 2506952 (Open Web Text)

Max Activating Token Index: 976

Text #3

Max Range: 4.7602. Min Range: -4.7602

Max Act: 4.5494. Min Act: -0.1700

Data Index: 7134742 (Open Web Text)

Max Activating Token Index: 732

Text #4

Max Range: 4.7602. Min Range: -4.7602

Max Act: 4.5790. Min Act: -0.1700

Data Index: 4597269 (Open Web Text)

Max Activating Token Index: 135

Text #5

Max Range: 4.7602. Min Range: -4.7602

Max Act: 4.5812. Min Act: -0.1700

Data Index: 4799974 (Open Web Text)

Max Activating Token Index: 77

Text #6

Max Range: 4.7602. Min Range: -4.7602

Max Act: 4.5689. Min Act: -0.1700

Data Index: 4401100 (Open Web Text)

Max Activating Token Index: 740

Text #7

Max Range: 4.7602. Min Range: -4.7602

Max Act: 4.6024. Min Act: -0.1700

Data Index: 5614656 (Open Web Text)

Max Activating Token Index: 601

Text #8

Max Range: 4.7602. Min Range: -4.7602

Max Act: 4.5628. Min Act: -0.1700

Data Index: 7134737 (Open Web Text)

Max Activating Token Index: 369

Text #9

Max Range: 4.7602. Min Range: -4.7602

Max Act: 4.5814. Min Act: -0.1700

Data Index: 814381 (Open Web Text)

Max Activating Token Index: 404

Text #10

Max Range: 4.7602. Min Range: -4.7602

Max Act: 4.5176. Min Act: -0.1700

Data Index: 300988 (Open Web Text)

Max Activating Token Index: 179

Text #11

Max Range: 4.7602. Min Range: -4.7602

Max Act: 4.5282. Min Act: -0.1700

Data Index: 200999 (Open Web Text)

Max Activating Token Index: 708

Text #12

Max Range: 4.7602. Min Range: -4.7602

Max Act: 4.5598. Min Act: -0.1700

Data Index: 2599540 (Open Web Text)

Max Activating Token Index: 624

Text #13

Max Range: 4.7602. Min Range: -4.7602

Max Act: 4.5770. Min Act: -0.1700

Data Index: 1492760 (Open Web Text)

Max Activating Token Index: 305

Text #14

Max Range: 4.7602. Min Range: -4.7602

Max Act: 4.5369. Min Act: -0.1700

Data Index: 8229789 (Open Web Text)

Max Activating Token Index: 427

Text #15

Max Range: 4.7602. Min Range: -4.7602

Max Act: 4.4933. Min Act: -0.1700

Data Index: 3647393 (Open Web Text)

Max Activating Token Index: 604

Text #16

Max Range: 4.7602. Min Range: -4.7602

Max Act: 4.4586. Min Act: -0.1700

Data Index: 1241531 (Open Web Text)

Max Activating Token Index: 106

Text #17

Max Range: 4.7602. Min Range: -4.7602

Max Act: 4.4956. Min Act: -0.1700

Data Index: 7215985 (Open Web Text)

Max Activating Token Index: 94

Text #18

Max Range: 4.7602. Min Range: -4.7602

Max Act: 4.4984. Min Act: -0.1700

Data Index: 7909811 (Open Web Text)

Max Activating Token Index: 442

Text #19

Max Range: 4.7602. Min Range: -4.7602

Max Act: 4.4979. Min Act: -0.1700

Data Index: 1279454 (Open Web Text)

Max Activating Token Index: 615